In September 1992, the band Blind Melon released their self-titled debut album. The record was mostly ignored until a music video for the song “No Rain”, featuring a girl in glasses dressed as a bumblebee, went berserk on MTV. The song rocketed up the Billboard Hot 100 charts. But that was the last time the band ever struck gold. 2 decades later, Rolling Stone named “No Rain” one of the biggest one-hit wonders of all time.
Soon after Blind Melon topped the charts, another artist had a breakout moment. Shania Twain released her second album, The Woman in Me, which included the No. 1 hit “Any Man of Mine”. Whatever the polar opposite of an one-hit wonder is, that’s what Shania Twain turned out to be. She became one of the most consistent hitmakers of her era, and the only female artist ever with 3 straight albums certified Diamond, meaning more than 10 million copies sold.
…He used an algorithm developed by the company EchoNest to measure the songs’ sonic features, including key, tempo, and danceability. This allowed him to quantify how similar a given hit is to the contemporary popular-music landscape (which he calls “novelty”), and the musical diversity of an artist’s body of work (“variety”).
“Novelty is a double-edged sword”, Berg told me. “Being very different from the mainstream is really, really bad for your likelihood of initially making a hit when you’re not well known. But once you have a hit, novelty suddenly becomes a huge asset that is likely to sustain your success.” Mass audiences are drawn to what’s familiar, but they become loyal to what’s consistently distinct.
Blind Melon’s “No Rain” rated extremely low on novelty in Berg’s research. Dreamy, guitar-driven soft rock wasn’t exactly innovative in 1992. According to Berg, this was the sort of song that was very likely to become an one-hit wonder: It rose to fame because of a quirky music video, not because the song itself stood out for its uniqueness. After that hit, the band struggled to distinguish their sound from everything else that was going on in music.
By contrast, Twain’s breakout hit rated high on novelty in Berg’s research. She was pioneering a new pop-country crossover genre that was bold for her time but would later inspire a generation of artists, like Taylor Swift. “Twain is a great fit for the model, because her blending of pop and country was so original before she had her breakout”, Berg told me. After her second album, he said, her novelty, which had previously been an artistic risk, helped her retain listeners. She could experiment within the kingdom of country-pop without much competition from other artists, and this allowed her to dominate the charts for the next decade.
Berg’s research also found that musical variety (as opposed to novelty) was useful for artists before they broke out. But down the line, variety wasn’t very useful, possibly because audience expectations are set by initial hits. “After the first hit, the research showed that it was good for artists to focus on what I call relatedness, or similarity of music”, he said. Nobody wants Bruce Springsteen to make a rap album.
[media] Creative industries produce many one-hit wonders who struggle to repeat their initial success and fewer hit makers who sustain success over time.
To develop theory on the role of creativity in driving sustained market success, I propose a path dependence theory of creators’ careers that considers creators’ whole portfolios of products over time and how their early portfolios shape their later capacity to sustain success. The main idea is that a creator’s path to sustained success depends on the creativity in their portfolio at the time of their initial hit—relatively creative portfolios give creators more options for leveraging their past portfolios while adapting to market changes, increasing their odds of additional hits.
I tested the proposed theory using an archival study of the U.S. music industry from 1959–2010, including data on over 3 million songs by 69,050 artists.
The results largely support the hypotheses. Artists who reached their initial hits with relatively creative (novel or varied) portfolios were more likely to generate additional hits, but a novel portfolio was less likely to yield an initial hit than was a typical portfolio.
These findings suggest that new creators face a tradeoff between their likelihood of initial versus sustained success, such that building a relatively creative early portfolio is a risky bet that can make or break a creator’s career.
Are there universal patterns in musical preferences?
To address this question, we built on theory and research in personality, cultural, and music psychology to map the terrain of preferences for Western music using data from 356,649 people across 6 continents.
In Study 1 (n = 284,935), participants in 53 countries completed a genre favorability measure, and in Study 2 (n = 71,714), participants in 36 countries completed an audio-based measure of preferential reactions to music. Both studies included self-report measures of the Big Five personality traits and demographics.
Results: converged to show that individual differences in preferences for Western music can be organized in terms of 5 latent factors that are invariant (ie. universal) across countries and that generalize across assessment methods. Furthermore, the patterns of correlations between personality traits and musical preferences were largely consistent across countries and assessment methods. For example, trait Extraversion was correlated with stronger reactions to Contemporary musical styles (which feature rhythmic, upbeat, and electronic attributes), whereas trait Openness was correlated with stronger reactions to Sophisticated musical styles (which feature complex and cerebral attributes often heard in improvisational and instrumental music). The patterns of correlations between musical preferences and gender differences, ethnicity, and other sociodemographic metrics were also largely invariant across countries.
Together, these findings strongly suggest that there are universal patterns in preferences for Western music, providing a foundation on which to develop and test hypotheses about the interactions between music, psychology, biology, and culture.
Introduction: Implementation of wastewater surveillance at music festivals has been limited to date. We aimed to use wastewater analysis and a self-report survey to determine the range of psychoactive substances being used during a music festival season in New South Wales, Australia.
Methods: We sampled 6 single-day music festivals requiring a music festival license in New South Wales from March 2019 to March 2020; between 15% and 100% of portaloos (temporary, un-fixed toilet facilities) were sampled at each festival. Samples were screened for 98 psychoactive substances and/or their metabolites with results qualitatively expressed as detection frequencies for each substance at each festival and across all festivals. We compared these data with the results of surveys of self-reported drug use at 4 of the 6 festivals.
Discussion: The detection frequency for cathinones was higher than expected relative to recent other data sources and this may represent adulteration or substitution. Similarly, the appearance of etizolam may be related to the use of counterfeit alprazolam. The detection of highly toxic substances such as n-ethylpentylone and norfentanyl may warrant public health alerts.
Conclusion: If provided close to real time, wastewater analysis at festivals could be complemented with information sources such as drug checking, on-site surveys, medical presentations and intelligence from peer networks to feed into early warning systems, public health alerts and peer-based harm reduction education during the festival season.
Moving in synchrony to the beat is a fundamental component of musicality. Here, we conducted a genome-wide association study (GWAS) to identify common genetic variants associated with beat synchronization in 606,825 individuals. Beat synchronization exhibited a highly polygenic architecture, with sixty-nine loci reaching genome-wide statistical-significance (p < 5×10−8) and SNP-based heritability (on the liability scale) of 13%–16%. Heritability was enriched for genes expressed in brain tissues, and for fetal and adult brain-specific gene regulatory elements, underscoring the role of central nervous system-expressed genes linked to the genetic basis of the trait. We performed validations of the self-report phenotype (through internet-based experiments) and of the GWAS (polygenic scores for beat synchronization were associated with patients algorithmically classified as musicians in medical records of a separate biobank). Genetic correlations with breathing function, motor function, processing speed, and chronotype suggest shared genetic architecture with beat synchronization and provide avenues for new phenotypic and genetic explorations.
Music streaming platforms can affect artists’ success through playlist ranking decisions.
Dominant platforms may exercise their power in a biased fashion.
We test for bias in Spotify’s New Music playlist rankings using outcome-based tests.
We find that Spotify’s New Music rankings favor indie-label music and music by women.
Despite challenges faced by women and indie artists, Spotify’s New Music curation appears to favor them.
Platforms are growing increasingly powerful, raising questions about whether their power might be exercised with bias.
While bias is inherently difficult to measure, we identify a context within the music industry that is amenable to bias testing. Our approach requires ex ante platform assessments of commercial promise—such as the rank order in which products are presented—along with information on eventual product success. A platform is biased against a product type if the type attains greater success, conditional on ex ante assessment. Theoretical considerations and voiced industry concerns suggest the possibility of platform biases in favor of major record labels, and industry participants also point to bias against women.
Using data on Spotify curators’ rank of songs on New Music Friday playlists in 2017, we find that Spotify’s New Music Friday rankings favor independent-label music, along with some evidence of bias in favor of music by women.
Despite challenges that independent-label artists and women face in the music industry, Spotify’s New Music curation appears to favor them.
[Keywords: online platforms, platform power, platform bias, music streaming, playlists]
Information steganography is a family of techniques that hide secret messages into a carrier; thus, the messages can only be extracted by receivers with a correct key Although many approaches have been proposed to achieve this purpose, historically, it is a difficult problem to conceal a large amount of information without occasioning human perceptible changes.
In this paper, we explore the room introduced by the low-rank property of natural signals (ie. images, audios), and propose a training-free model for efficient information steganography, which provides a capacity of hiding full-size images into carriers of the same spatial resolution. The key of our method is to randomly shuffle the secrets and carry out a simple reduction summation with the carrier. On the other hand, the secret images can be reconstructed by solving a convex optimization problem similar to the ordinary tensor decomposition.
In the experimental analysis, we carry out 2 tasks: concealing a full-RGB-color image into a gray-scale image; concealing images into music signals. The results confirm the ability of our model to handle massive secret payloads.
Language and music are two human-unique capacities whose relationship remains debated. Some argue for overlap in processing mechanisms, especially for structure processing, but others fail to find overlap. Using fMRI, we examined the responses of language brain regions to diverse music stimuli, and also probed the musical abilities of individuals with severe aphasia. Across four experiments, we obtained a clear answer: music does not recruit nor requires the language system. The language regions’ responses to music are generally low and never exceed responses elicited by non-music auditory conditions, like animal sounds. Further, the language regions are not sensitive to music structure: they show low responses to both intact and scrambled music, and to melodies with vs. without structural violations. Finally, individuals with aphasia who cannot judge sentence grammaticality perform well on melody well-formedness judgments. Thus the mechanisms that process structure in language do not appear to support music processing.
Prior to last month, I knew next to nothing about K-pop (Korean popular music) besides having heard a few songs in passing and the rumors of the industry’s infamous elements, most notably a string of high profile suicides over the last few years. As an American with no connection to music or South Korean culture, I wondered if I was getting an accurate picture of the industry or if I was being misled by the most lurid and morbid elements eagerly conveyed by the media.
The Basics
“K-pop” is both a genre of music and an entire industry which “manufacturers” performers and their performance output (music, dance routines, shows, merchandise, etc.) in a highly systematized top-down manner
The global popularity of K-pop is extraordinary considering the relatively small population of South Korea, and the relatively small size of K-pop production companies
The Product
K-pop’s industrial/corporate structure represents a Korean (and East-Asian) cultural alternative to Western pop and broader music production
K-pop stars and bands are manufactured and controlled by production companies in the same manner Western athletes are trained and traded by sports teams.
K-pop stars are crafted into idealized portrays of individuals by East Asian cultural standards
The Fans
K-pop fandom is both more intense on average than Western fandom, and has a larger percentage of unhealthily obsessive fans
K-pop stars are forced to abide by extremely restrictive behavioral norms to appease production companies and fans
The Process
Trying to become a K-pop star is a terrible idea by any rational cost-benefit analysis
The process by which production companies train K-pop stars is abusive and depends on the ignorance of children/teenagers and clueless and/or malicious parents
Even after making it through the extraordinarily difficult audition and training process, the vast majority of K-pop stars will have short careers and earn little or possibly no money
The Machine
K-pop is an extremely centralized, hierarchical industry, where structural, business, and creative decisions are almost entirely made by corporate management, rather than the performers
Raw creativity in the music production process is largely outsourced to Westerners who write, produce, and choreograph the music
The K-pop industry is subsidized and supported by the South Korean government, if not implicitly or explicitly directed, as a conscious form of soft power projection and social control.
As you can tell, I came away from my research with a negative view of K-pop. I don’t think it’s the worst thing in the world, but I find its fandom to be unhealthy and its production process to be exploitative. That being said, there are undoubtedly many tremendous talents in the K-pop world and the cultural power of K-pop is remarkable.
Music comprises a diverse category of cognitive phenomena that likely represent both the effects of psychological adaptations that are specific to music (eg. rhythmic entrainment) and the effects of adaptations for non-musical functions (eg. auditory scene analysis). How did music evolve?
Here, we show that prevailing views on the evolution of music—that music is a byproduct of other evolved faculties, evolved for social bonding, or evolved to signal mate quality—are incomplete or wrong.
We argue instead that music evolved as a credible signal in at least two contexts: coalitional interactions and infant care. Specifically, we propose that (1) the production and reception of coordinated, entrained rhythmic displays is a co-evolved system for credibly signaling coalition strength, size, and coordination ability; and (2) the production and reception of infant-directed song is a co-evolved system for credibly signaling parental attention to secondarily altricial infants.
These proposals, supported by interdisciplinary evidence, suggest that basic features of music, such as melody and rhythm, result from adaptations in the proper domain of human music.
The adaptations provide a foundation for the cultural evolution of music in its actual domain, yielding the diversity of musical forms and musical behaviors found worldwide.
The Birth of a Nation set the pace for a century of Wagnerian aggression on film. More than a thousand movies and TV shows feature the composer on their soundtracks, yoking him to all manner of rampaging hordes, marching armies, swashbuckling heroes, and scheming evildoers. The “Ride of the Valkyries” turns up in a particularly dizzying variety of scenarios. In “What’s Opera, Doc?”, Elmer Fudd chants “Kill da wabbit” while pursuing Bugs Bunny. In John Landis’s The Blues Brothers (1980), the “Ride” plays while buffoonish neo-Nazis chase the heroes down a highway and fly off an overpass. Most indelibly, Francis Ford Coppola’s Apocalypse Now (1979) upends Griffith’s racial duality, making white Americans the heralds of destruction: a helicopter squadron blares the “Ride” as it lays waste to a Vietnamese village.
Action sequences are only one facet of Wagner’s celluloid presence. A colorful—and often shady—array of Wagner enthusiasts have appeared onscreen, from the woebegone lovers of Robert Siodmak’s noir Christmas Holiday to the diabolical android of Ridley Scott’s Alien: Covenant. The composer himself is portrayed in more than a dozen movies, including Tony Palmer’s extravagant, eight-hour 1983 bio-pic, starring Richard Burton. But the Wagnerization of film goes deeper than that. Cinema’s integration of image, word, and music promised a fulfillment of the idea of the Gesamtkunstwerk, or “total work of art”, which Wagner propagated at one stage of his career. His informal system of assigning leitmotifs to characters and themes became a defining trait of film scores. And Hollywood has drawn repeatedly from Wagner’s gallery of mythic archetypes: his gods, heroes, sorcerers, and questers…Wagner’s influence is nowhere more enduring than in the realm of myth and legend. He manipulated Teutonic and Arthurian myths with consummate dexterity, understanding how they could resonate allegorically for modern audiences. “The incomparable thing about myth is that it is always true, and its content, through utmost compression, is inexhaustible”, he wrote. Wagner’s master array of borrowed, modified, and reinvented archetypes—the wanderer on a ghost ship, the savior with no name, the cursed ring, the sword in the tree, the sword reforged, the novice with unsuspected powers—lurks behind the blockbuster fantasy and superhero narratives that hold sway in contemporary Hollywood.
…This contradictory swirl of associations mirrors the composer’s fractured legacy: on the one hand, as a theatrical visionary who created works of Shakespearean breadth and depth; on the other, as a vicious anti-Semite who became a cultural totem for Hitler. Like operagoers across the generations, filmmakers have had trouble deciding whether Wagner is an inexhaustible store of wonder or a bottomless well of hate. But that uncertainty also mirrors the film industry’s own ambiguous role as an incubator of heroic fantasies, which can serve a wide range of political ends. When Hollywood talks about Wagner, it is often—consciously or not—talking about itself.
…Bayreuth’s technical achievements predicted cinematic sleights of hand. In the Ring, magic-lantern projections evoked the Valkyries on their flying steeds; in Parsifal, the Grail glowed with electric light. Clouds of steam generated by two locomotive boilers smoothed over changes of scene, in anticipation of the techniques of dissolve and fade-out. Wagner’s music itself provides hypnotic continuity. When the action of Das Rheingold shifts from the Rhine to the area around Valhalla, the stage directions say, “Gradually the waves turn into clouds, which resolve into a fine mist.” In the score, rushing river patterns give way to shimmering tremolos and then to a more rarefied texture of flutes and violins—what the scholar Peter Franklin describes as an “elaborate upward panning shot.” In the descent into Nibelheim, the realm of the dwarves, the sound of hammering anvils swells in a long crescendo before fading away. This is like a dolly shot: a camera moves in on the Nibelungs at work, then draws back.
Advances in digital technology have put music libraries at people’s fingertips, giving them immediate access to more music than ever before.
Here we overcome limitations of prior research by leveraging ecologically valid streaming data: 17.6 million songs and over 662,000 hr of music listened to by 5,808 Spotify users spanning a 3-month period.
Building on interactionist theories, we investigated the link between personality traits and music listening behavior, described by an extensive set of 211 mood, genre, demographic, and behavioral metrics. Findings from machine learning showed that the Big Five personality traits are predicted by musical preferences and habitual listening behaviors with moderate to high accuracy.
Importantly, our work contrasts a recent self-report-based meta-analysis, which suggested that personality traits play only a small role in musical preferences; rather, we show with big data and advanced machine learning methods that personality is indeed important and warrants continued rigorous investigation.
…Prediction: Mean of the RMSE from 10× cross-validation showed moderate to high prediction for each of the Big Five personality traits: .811 for Extraversion, 0.777 for Emotional Stability, .621 for Agreeableness, 0.618 for conscientiousness, and .530 for Openness. Independent regressions were then performed for each trait. Table 1 summarizes our prediction results (rs range from 0.262 to 0.374). These results are greater in magnitude than those found in previous research by Nave et al 2018 that use stimuli-based methods and Facebook likes to assess musical preferences. That our results yielded higher correlations is not surprising since we included metrics that assessed not only musical preferences but also habitual listening behaviors…Of the 5 personality traits, Emotional Stability and Conscientiousness were the 2 most predictable from our data (rs = 0.374 and 0.363, respectively).
Music listening plays an important role in the daily lives of many. It remains unclear what explains variation in how much time people spend listening to music and whether music listening improves musical auditory discrimination skills.
In 10,780 Swedish twin individuals, data were available on hours of music listening, musical engagement and musical auditory discrimination.
Genetic and shared environmental factors together explain half of the variation in music listening in both sexes. Hours of music listening was positively associated with musical auditory discrimination in both sexes and this effect was independent of whether individuals played a musical instrument. However, the effect disappeared when applying a co-twin control analysis to control for genetic and shared environmental confounding.
These findings suggest that music listening may not causally improve musical auditory discrimination skills, but rather that the association is likely due to shared familial factors.
[Keywords: music listening, musical auditory discrimination, genetics, shared environment, twins]
How do elites signal their superior social position via the consumption of culture? We address this question by drawing on 120 years of “recreations” data (n = 71,393) contained within Who’s Who, an unique catalogue of the British elite…In November 2016, after extensive discussions with Oxford University Press and Bloomsbury Publishing—the 2 publishing companies producing Who’s Who—we successfully brokered access to all data collected by the publication since it began including full biographical details in 1897…Finally, to provide a more granular analysis of elite musical taste, we combine Who’s Who with another unique historical data source—the archive of Desert Island Discs, a radio show broadcast on the BBC since 1942 (Brown et al 2017; Dean et al 2018; Thurman 2012). The format of the show is straightforward. Each week a “castaway”—usually a noteworthy and influential elite person—is asked to choose 8 songs or pieces of music they would take with them if they were to be stranded on a desert island. As over 60% of the people who have appeared on Desert Island Discs are also in Who’s Who, we are able to merge the 2 datasets to provide a more granular analysis of the music tastes of around 1,200 Who’s Who entrants.
Our results reveal 3 historical phases of elite cultural distinction: first, a mode of aristocratic practice forged around the leisure possibilities afforded by landed estates, which waned substantially in the late-19th century; second, a highbrow mode dominated by the fine arts, which increased sharply in the early-20th century before gently receding in the most recent birth cohorts; and, third, a contemporary mode characterized by the blending of highbrow pursuits with everyday forms of cultural participation, such as spending time with family, friends, and pets.
These shifts reveal changes not only in the contents of elite culture but also in the nature of elite distinction, in particular, (1) how the applicability of emulation and (mis)recognition theories has changed over time, and (2) the emergence of a contemporary mode that publicly emphasizes everyday cultural practice (to accentuate ordinariness, authenticity, and cultural connection) while retaining many tastes that continue to be (mis)recognized as legitimate.
…Our analysis begins by identifying a mode of aristocratic elite culture, dominant in the late-19th century, that was forged around the leisure possibilities afforded by landed estates (eg. shooting, hunting, horse riding, polo, sailing). Here elites achieved distinction via the emulation of lower yet aspirational social groups, who largely deferred to their authority as inherent cultural paragons. We then show how this mode was threatened at the turn of the 20th century. “Nouveau riche” industrialists began to buy their way into high society, and existing aristocratic elites, battling economic upheaval, were unable to guard against this pecuniary emulation. Next, we show how a new generation of elites—influenced in particular by the Bloomsbury intellectual collective—adapted to this threat. Positioning itself against the philistinism of aristocratic modes, this new cohort championed a set of emerging “high” cultural forms (eg. theater, ballet, classical music, abstract art) that went on to define elite culture in the 1920s, 1930s, and 1940s. This new highbrow mode was successful in delivering distinction, albeit via a different mechanism. Rather than relying on an ascribed cultural legitimacy, as in the emulation model, highbrow elites instead focused on generating a widespread (mis)recognition, via the state and allied institutions such as the BBC, of the inherent value of their own tastes and recreations. Again, though, this mode of elite culture was eventually questioned. Beginning in the 1950s, the supremacy of highbrow culture was threatened by shifts within the art-world that initially challenged the highbrow aesthetic and later legitimized certain popular cultural forms; generational value change that precipitated a decline in snobbery and deference (to elites); and the emergence of a managerial culture where access to a broad cultural repertoire functioned as a key resource.
The final part of our analysis explains how once again elites adapted to these threats, diversifying their cultural profiles and increasingly blending highbrow (and some aristocratic) recreations with popular tastes and a range of everyday practices, such as spending time with family, friends, and pets. We interpret this contemporary mode as pursuing dual aims. First, it continues to be distinction-seeking, with popular tastes still tilting toward more legitimate artists. However, the growing expression of everyday recreations, we argue, also signals something beyond distinction, and peculiar to the particular moral threats facing contemporary elites. As elites pull away economically, they face increasing suspicion from wider publics that they lack prosocial motives and, in turn, authenticity and moral character. The public expression of such “ordinary” everyday practices, therefore, with their intrinsic rather than extrinsic reward association, acts as a way to plug this authenticity-insecurity.
…Second, we go further to examine the legitimacy of the popular music being played. Specifically, we examined the critical-acclaim of musical artists by analyzing their average score on the music website Metacritic, which aggregates reviews of albums. Figure 6 shows that the artists played by Who’s Who entrants are consistently more legitimate, in terms of their mean Metacritic score, than the average musical artist.25 Indeed, they are consistently in the top quartile. This indicates that although contemporary elites may be increasingly integrating popular cultural forms into their cultural repertoires, the individual artists they prefer still tilt toward the legitimate and consecrated.
[Long profile by a journalist who joined him on tour of the career and personage of Alfred Matthew Yankovic, the most famous and long-lived comedic music musician in the world, lasting where other novelty hits have long since faded; over the past 44 years, after emerging from a hilariously-repressed childhood, his parodies have become an institution and a marker of pop/rock music success.
Why is he so popular? Weird Al appeals to weird outsiders and the unappreciated by deflating the pretensions of rock stars, by being incorrigibly nice and dedicated to his fans despite being deeply introverted, and because he is a genuinely talented performer who gives great concerts and spends months agonizingly perfecting every last lyric of his parodies.]
“Yankovic with 232 fans on January 18, 2020.”
…The connection is so deep that it is more like a merging, and after a while it struck me that Weird Al has spent basically his whole life making his music for exactly these people, which is to say for his childhood self. For many decades, he has been trying to delight Alfred Yankovic, the bright, painfully shy kid who grew up alone in his tiny bedroom. For the benefit of that lonely boy, he reshaped the whole world of pop culture. His ridiculous music sent out a pulse, a signal, and these were the people it drew: the odd, the left out. A crowd of friends for that lonely kid. As I watched him with his fans, sometimes I felt as if Weird Al was multiplying all around me, multiplying inside of me. We were one crowd, united in isolation, together in a great collective loneliness that—once you recognized it, once you accepted it—felt right on the brink of being healed.
Radio remains popular, delivering an audience reach of over 90%, but radio ratings may overestimate real advertising exposure. Little is known about audience and media factors affecting radio-advertising avoidance. Many advertisers have believed as much as 1⁄3rd of the audience switch stations during radio-advertising breaks.
In the current study, the authors combined Canadian portable people-meter data ratings to measure loss of audience during advertising. They discovered a new benchmark of 3% (across conditions) for mechanical (or actual physical) avoidance of radio advertising, such as switching stations or turning off the radio.
This rate is about one-tenth of current estimates, but was higher for music versus talk stations, out-of-home versus in-home listening, and early versus late dayparts.
New entrants in established markets face competing recommendations over whether it is better to establish their legitimacy by conforming to type or to differentiate themselves from incumbents by proposing novel contributions. This dilemma is particularly acute in cultural markets in which demand for novelty and attention to legitimacy are both high. We draw upon research in organizational theory and entrepreneurship to hypothesize the effects of pursuing narrow or broad appeals on the performance of new entrants in the music industry. We propose that the sales of novel products vary with the distance perceived between the classes being combined and that this happens, in part, because combinations that appear to span great distances encourage consumers to adopt superordinate rather than subordinate classes (eg. to classify and evaluate something as a “song” rather than a “country song”). Using a sample of 144 artists introduced to the public via the U.S. television program The Voice, we find evidence of a U-shaped relationship between category distance and consumer response. Specifically, consumers reward new entrants who pursue either familiarity (ie. nonspanning) or distinctive combinations (ie. combine distant genres) but reject efforts that try to balance both goals. An experimental test validates that manipulating the perceived distance an artist spans influences individual evaluations of product quality and the hierarchy of categorization. Together these results provide initial evidence that distant combinations are more likely to be classified using a superordinate category, mitigating the potential confusion and legitimacy-based penalties that affect middle-distance combinations.
[The Browser summary: “The amazing life of Alma Mahler. She married and/or romanced Gustav Mahler, Oskar Kokoschka, Walter Gropius and Franz Werfel. She was”anti-Semitic, narcissistic, boastful, and untruthful”. Was she also an “ambitious young woman who longed to be a great composer but became instead a great muse to great men?”. Was she an “artist stunted by society’s restrictions on women?”. Was she a “grandiose groupie, expropriating the fame of her husbands and lovers?” Perhaps uniquely, she was all three.” Mahler’s life dramatized the Viennese milieu, with absurd melodrama.]
The Alma Schindler of her early diaries, which she began in 1898, is, indeed, appealing. They reveal an ebullient teenager full of serious opinions and enthusiasms, a flirtatious young woman giddy with the attentions of the cultural elite in culturally elite fin-de-siècle Vienna. Alma writes about crushes and kisses and assignations on the Ringstrasse, about vigorously practicing the piano and earnestly studying composition, about attending the opera, about buying dresses and fighting with her mama. She is a girl—a splendid girl in a splendid city at a splendid time. She is vain and unsure of herself, self-aggrandizing as only a serious, determined, sensitive young person can be. The early diaries, published in English in 1998, end in 1902, just before she married Gustav Mahler. Alma lived for another sixty-two years, years of vainglorious strutting, scheming, and disloyalty, years chronicled by her own memoirs and by her later diaries (which have not been translated into English). Mahler scholars have a name for the challenge that arises from her unreliable tendencies: the Alma Problem. “She is routinely accused of massaging the facts to serve her own legacy”, Haste writes, “of suppressing or editing her husband Gustav Mahler’s published letters to remove critical references to her, for instance—acts seen, particularly by Mahler scholars (for whom she was for some time their principal source), as tampering with the archive.”…Touched by her husband’s new devotion and convinced that he would die if she left him, Alma sent Gropius away. Gustav wrote her daily love poems, smothered her slippers in kisses, and listened again to her music, pronouncing it good and begging her to resume composing. Alma was undeniably talented, and her songs are admired today, but this episode points as much to her extraordinary power as a muse as to her gifts as an artist. Her daughter Anna said that when Alma
just stopped in the doorway, you could immediately feel an electric charge… She was an incredibly passionate woman… And she really paid attention to everyone she spoke to. And encouraged them… She was able to enchant people in a matter of seconds.
Albrecht Joseph, eventually Anna’s fifth husband, who was shocked by Alma’s dowdiness when he first met the legendary seductress in 1931, nevertheless noted that her “unique gift” was “a profound, uncanny understanding of what it was that [creative] men tried to achieve, an enthusiastic, orgiastic persuasion that they could do what they aimed at, and that she, Alma, fully understood what it was.” The intensity of her belief in art and genius had the effect of creating an almost violent sympathy. Gustav, like the other men she loved, did not think he could survive artistically without her. ·…And then there was Kokoschka. Alma later described her three-year affair with Oskar Kokoschka as “one violent struggle of love. Never before had I experienced so much strain, so much hell and so much paradise.” Jealous and controlling, the artist stalked her, patrolling her street after he left her house to make sure no other man visited. She refused to marry him, so while she was in Paris he stole her documents and posted the banns in the Döbling parish hall. “Oskar Kokoschka could only make love to me with the most peculiar game playing”, she later wrote. “As I refused to hit him during our hours of love, he began conjuring up the most appalling images of murder” of his supposed rivals “while whispering murkily to himself.” One night when she sang Parsifal at the piano, he whispered “a new, eerie text” into her ear, which caused her to scream and cry, then to swallow a toxic dose of bromine. (Kokoschka called the doctor.) · And through it all, he painted her. When she had an abortion (she wrote that she was afraid of “what might grow in me”), Kokoschka took a blood-stained cotton pad from her and kept it with him, saying, “That is, and will always be, my only child.” He painted bloody, murdered children. He drew “Alma Mahler Spinning with Kokoschka’s Intestine.” He insisted that she cover her arms with long sleeves. Kokoschka painted Alma entwined with him in a boat on a stormy sea, he painted Alma rising to the heavens while he stood in hell surrounded by snakes. Anna watched him work and asked, “Can’t you paint anything else except Mommy?” · When war came, Alma’s reaction was, as even the temperate Haste must admit, “an astonishing flourish of self-aggrandizement.” “I sometimes imagine”, Alma wrote, “that I was the one who ignited this whole world conflagration in order to experience some kind of development or enrichment—even if it be only death.” By now, she wanted to purify herself of the “evil fascination” of Kokoschka. She taunted him until he joined the cavalry, then broke off their relationship in unkind letters. In despair, Kokoschka insisted on being sent to the front, where he was wounded so badly he was reported dead in the Viennese papers. Though she later defiantly published a facsimile of Mahler’s manuscript of his Tenth Symphony, revealing (for a good price) his intimate, despairing notes, she was less keen on allowing her own letters to reach the public. After rushing to Kokoschka’s studio with her set of keys, she removed and burned her notes to him. · Though Kokoschka had not in fact died, her interest in him had. She was back to writing letters to Gropius. When she saw him while he was on leave, Haste writes, “their passion was rekindled”, and they got married. Kokoschka dealt with this rejection by commissioning a life-sized Alma doll, with instructions to “please make it possible that my sense of touch will be able to take pleasure in those parts where the layers of fat and muscle suddenly give way to a sinuous covering of skin.” The doll, covered in fluffy swan skin, suffered an ignominious end, beheaded and bedraggled in a courtyard the morning after Kokoschka threw a raucous farewell party for it.
Music training has repeatedly been claimed to positively impact on children’s cognitive skills and academic achievement. This claim relies on the assumption that engaging in intellectually demanding activities fosters particular domain-general cognitive skills, or even general intelligence. The present meta-analytic review (n = 6,984, k = 254, m = 54) shows that this belief is incorrect. Once the study quality design is controlled for, the overall effect of music training programs is null (g ≈ 0) and highly consistent across studies (τ2 ≈ 0). Small statistically-significant overall effects are obtained only in those studies implementing no random allocation of participants and employing non-active controls (g ≈ 0.200, p < 0.001). Interestingly, music training is ineffective regardless of the type of outcome measure (eg. verbal, non-verbal, speed-related, etc.). Furthermore, we note that, beyond meta-analysis of experimental studies, a considerable amount of cross-sectional evidence indicates that engagement in music has no impact on people’s non-music cognitive skills or academic achievement. We conclude that researchers’ optimism about the benefits of music training is empirically unjustified and stem from misinterpretation of the empirical data and, possibly, confirmation bias. Given the clarity of the results, the large number of participants involved, and the numerous studies carried out so far, we conclude that this line of research should be dismissed.
The 1-bit sonic environment (perhaps most famously musically employed on the ZX Spectrum) is defined by extreme limitation. Yet, belying these restrictions, there is a surprisingly expressive instrumental versatility. This article explores the theory behind the primary, idiosyncratically 1-bit techniques available to the composer-programmer, those that are essential when designing “instruments” in 1-bit environments. These techniques include pulse width modulation for timbral manipulation and means of generating virtual polyphony in software, such as the pin pulse and pulse interleaving techniques. These methodologies are considered in respect to their compositional implications and instrumental applications.
Alban Berg’s bleak opera “Wozzeck” might not seem suited to the holiday season. One of the least cheerful pieces in the repertory, it tells the story of an impoverished and increasingly delusional soldier, driven to murder and suicide. Yet this time of year is also a moment to take stock. And few works look at life with more searing honesty than “Wozzeck.” The issues that drive this wrenching, profound opera are especially timely: the impact of economic inequality on struggling families; the looming threats of war and environmental destruction; the rigid stratification—almost the militarization—of every element of society.
…The opera—which unfolds in 15 short, episodic scenes—is played atop a set (designed by Sabine Theunissen) built of platforms connected by rickety walkways, evoking a bombed-out city amid consuming chaos. Silent actors, most in gas masks, keep appearing here and there. An almost continual montage of animation, drawings and projections, mostly in black and white, appear on and behind the set: images of blown-up churches and buildings; military maps; charcoal drawings of bedraggled people morphing into spectral stick figures; despoiled rivers and hills. In the first scene, rather than shaving his officious captain, as indicated in the libretto, Wozzeck here is operating a small movie camera that projects cartoonish images of people on a small screen. Mr. Kentridge said in a recent interview with The New York Times that he conceived the action of the opera as taking place within that projection.
…The carousing at a seedy tavern, where the crazed Wozzeck shows up after stabbing Marie, was all the more eerie for the multilayered setting and the ominous costumes (by Greta Goiris), with the crowd in gas masks, a bitter premonition of the war to come…One of the daring elements of the production is the depiction of Wozzeck and Marie’s young son as a simple puppet, wearing ragged clothes and a gas mask. Mr. Kentridge said in the interview that using real children in crucial roles can be distracting. But I have found it moving to see a boy in the role—especially in the final scene when, riding a hobby horse, he finally follows the townspeople, who have discovered the body of his mother offstage. Mr. Kentridge’s use of a puppet seems like a solution in search of a problem.
Experiments with OpenAI’s ‘preference learning’ approach, which trains a NN to predict global quality of datapoints, and then uses reinforcement learning to optimize that directly, rather than proxies. I am unable to improve quality, perhaps due to too-few ratings.
Standard language generation neural network models, like GPT-2, are trained via likelihood training to imitate human text corpuses. Generated text suffers from persistent flaws like repetition, due to myopic generation word-by-word, and cannot improve on the training data because they are trained to predict ‘realistic’ completions of the training data.
A proposed alternative is to use reinforcement learning to train the NNs, to encourage global properties like coherence & lack of repetition, and potentially improve over the original corpus’s average quality. Preference learning trains a reward function on human ratings, and uses that as the ‘environment’ for a blackbox DRL algorithm like PPO.
OpenAI released a codebase implementing this dual-model preference learning approach for textual generation, based on GPT-2. Having previously used GPT-2 for poetry & music generation, I experimented with GPT-2 preference learning for unconditional music and poetry generation.
I found that preference learning seemed to work better for music than poetry, and seemed to reduce the presence of repetition artifacts, but the results, at n ≈ 7,400 ratings compiled over 23 iterations of training+sampling November 2019–January 2020, are not dramatically better than alternative improvements like scaling up models or more thorough data-cleaning or more stringent sample curation. My blind ratings using n ≈ 200 comparisons showed no large advantage for the RL-tuned samples (winning only 93 of 210 comparisons, or 46%).
This may be due to insufficient ratings, bad hyperparameters, or not using samples generated with common prefixes, but I suspect it’s the former, as some NLP tasks in Ziegler et al 2019 required up to 60k ratings for good performance, and the reward model appeared to achieve poor performance & succumb to adversarial examples easily.
Working with it, I suspect that preference learning is unnecessarily sample-inefficient & data-inefficient, and that the blackbox reinforcement learning approach is inferior to directly using the reward model to optimize text samples, and propose two major architectural overhauls: have the reward model directly model the implied ranking of every datapoint, and drop the agent model entirely in favor of backprop-powered gradient ascent which optimizes sequences to maximize the reward model’s output.
Song lyrics are rich in meaning. In recent years, the lyrical content of popular songs has been used as an index of shifting norms, affect, and values at the cultural level. One remarkable, recently-uncovered trend is that successful pop songs have increasingly simple lyrics. Why?
We test the idea that increasing lyrical simplicity is linked to a widening array of novel song choices.
To test this Cultural Compression Hypothesis (CCH), we examined 6 decades of popular music (n = 14,661 songs).
The number of novel song choices predicted greater lyrical simplicity of successful songs. This relationship was robust, holding when controlling for critical ecological and demographic factors and also when using a variety of approaches to account for the potentially conconfoundingfluence of temporal autocorrelation.
The present data provide the first time series evidence that real-world cultural transmission may depend on the amount of novel choices in the information landscape.
[Keywords: cultural change, cultural evolution, music]
Collective memory and attention are sustained by two channels: oral communication (communicative memory) and the physical recording of information (cultural memory).
Here, we use data on the citation of academic articles and patents, and on the online attention received by songs, movies and biographies, to describe the temporal decay of the attention received by cultural products.
We show that, once we isolate the temporal dimension of the decay, the attention received by cultural products decays following an universal biexponential function.
We explain this universality by proposing a mathematical model based on communicative and cultural memory, which fits the data better than previously proposed log-normal and exponential models. Our results reveal that biographies remain in our communicative memory the longest (20–30 years) and music the shortest (about 5.6 years).
These findings show that the average attention received by cultural products decays following an universal biexponential function.
[Demonstration dialogue of interacting with a GPT-2-1.5b trained on text adventures/RPGs. The player chooses to join a band of orcs as a musician and tries to steer the game towards orc rights, with moderate success, reaching the Emperor himself.]
In the first AI Dungeon, we created and deployed a deep learning generated text adventure using OpenAI’s 124M parameter GPT-2 model. In the interest of computational cost, possible actions and their results were generated and given to the player to choose from.
In AI Dungeon 2 we do away with pregenerated actions and allow the user to enter any action. The model then continues generating the story resulting from that action. We also upgrade the size of our model to OpenAI’s largest 1.5B parameter model and fine-tune it on a collection of text adventures obtained from chooseyourstory.com. Following the example of the Salesforce CTRL model we also modified the sampling of our model to add a penalty to already generated words to reduce the repetition issues that GPT-2 has and enable a lower temperature setting.
When playing AI Dungeon 2 the player can choose from several possible settings and characters. These choices generate a starting prompt and context sentence. The context sentence is always included as input to the model to help keep it grounded to the chosen setting while the starting prompt is the beginning of the story.
[Dialogue sample:]
…After the Gnoll War ends, the orcs decide to hold a big celebration. You immediately organize concert to entertain everyone. It goes well and you even win a few awards for your work. However, you still aren’t satisfied and you decide to do something else.
> write plays for the orcs to perform in
You write a series of plays based on the stories of the orcs. These works are performed throughout the Empire and they are very popular. You also take an interest in the orcs’ future and begin to study their language and culture. In time you even develop a liking for the orcs themselves.
> found a human-orc friendship organization
While you were studying the orcs, you came across a group called the Human-Orc Friendship Association (HOOFA). While they weren’t exactly like the Orcs, they had similar goals. You decided to form a separate chapter just for them.
> write some pamphlets support orc-human friendship
You wrote a pamphlet explaining what the HOOFA was and how it worked. You also explained that the orcs were the only race that could truly understand each other and that humans were inferior to the orcs.
> promote inter-racial marriage between humans and orcs
In order to promote inter-racial marriage between humans and orcs, you started a branch of the HOOFA called the Inter-Race Marriage Bureau (IRMB) which was located in the city of Kishak…
Akhnaten, Philip Glass’ “Egyptian opera”, opening at the Metropolitan Opera this weekend, premiered in 1984 and since then has been produced in many different stagings, primarily in European cities, where the composer has a very large and enthusiastic audience. Akhnaten’s American production story has been much more modest.
…Someone at the party had told Glass that I was studying Egyptian language and culture. He sought me out, introduced himself and asked if I knew anything about Akhnaten, the “heretic Pharaoh.” The party had put me in a jocular mood and my immediate response was “know about him? I just saw him!” I explained that I had only recently returned from Cairo, where the massive statue of Akhnaten in the Cairo Museum was the Egyptian artifact that had made the deepest impression on me. (Later I realized that in my response I was channeling a skit in 2000 Year Old Man in which Carl Reiner asks Mel Brooks if he had known Joan of Arc. “What do you mean knew her”, said Brooks, “I dated her!”) Our initial conversation about Egypt and Akhnaten lasted for more than an hour.
In his remarkably creative way, Glass had been reading widely about Egypt and Akhnaten. He had studied James Henry Breasted’s authoritative History of Egypt and he read Freud’s speculations about Akhnaten in his last book, Moses and Monotheism. We agreed to meet the following week to continue our conversation. I told Glass that for our next meeting I would bring pictures of Akhnaten, his wife Nefertiti, and of his artistic creations. For Akhnaten was an artist and poet, as well as a Pharaoh—or at least that was the claim of some experts. Our subsequent meetings at which I was introduced to Glass’ theater and music collaborators, Robert Israel and Richard Riddell, went very well. They had worked with Glass on Satyagraha and were collaborating with him on the creation of Akhnaten. Asked by Glass if I would be able to serve as a researcher on his Egyptian project, I said yes.
…His formulation was: “Einstein as the man of science, Gandhi as the man of politics, Akhnaten as the man of religion.”
In his 1987 book, Music by Philip Glass, the composer explained his fascination with the heretic king: “On becoming Pharaoh, he declared a new religion based upon Aten, associated with the sun, but not actually the sun itself, a very important point theologically. His new god was supreme and alone, making Akhnaten the first declared monotheist in history….Finally, by not completely identifying his god with the physical sun but emphasizing his independent nature, Akhnaten’s god is the first truly abstract god head we know.” Glass knew that not all historians of religion and culture agreed with this description. But for Glass, the main point was that “Akhnaten had changed his (and our) world through the force of his ideas and not through the force of arms.”
Generating Irish/folk/classical music in ABC format using GPT-2-117M, with good results.
In November 2019, I experimented with training a GPT-2 neural net model to generate folk music in the high-level ABC music text format, following previous work in 2016 which used a char-RNN trained on a ‘The Session’ dataset. A GPT-2 hypothetically can improve on an RNN by better global coherence & copying of patterns, without problems with the hidden-state bottleneck.
I encountered problems with the standard GPT-2 model’s encoding of text which damaged results, but after fixing that, I successfully trained it on n = 205,304 ABC music pieces taken from The Session & ABCnotation.com. The resulting music samples are in my opinion quite pleasant. (A similar model was later retrained by Geerlings & Meroño-Peñuela 2020.)
The ABC folk model & dataset are available for download, and I provide for listening selected music samples as well as medleys of random samples from throughout training.
We followed the ABC folk model with an ABC-MIDI model: a dataset of 453k ABC pieces decompiled from MIDI pieces, which fit into GPT-2-117M with an expanded context window when trained on TPUs. The MIDI pieces are far more diverse and challenging, and GPT-2 underfits and struggles to produce valid samples but when sampling succeeds, it can generate even better musical samples.
It has been repeatedly reported that motivation for listening to music is majorly driven by the latter’s emotional effect. There is a relative opposition to this approach, however, suggesting that music does not elicit true emotions. Counteracting this notion, contemporary research studies indicate that listeners do respond affectively to music providing a scientific basis in differentially approaching and registering affective responses to music as of their behavioral or biological states. Nevertheless, no studies exist that combine the behavioral and neuroscientific research domains, offering a cross-referenced neuropsychological outcome, based on a non-personalized approach specifically using a continuous response methodology with ecologically valid musical stimuli for both research domains. Our study, trying to fill this void for the first time, discusses a relevant proof-of-concept protocol, and presents the technical outline on how to multimodally measure elicited responses on evoked emotional responses when listening to music. Specifically, we showcase how we measure the structural music elements as they vary from the beginning to the end within two different compositions, suggesting how and why to analyze and compare standardized, non-personalized behavioral to electroencephalographic data. Reporting our preliminary findings based on this protocol, we focus on the electroencephalographic data collected from n = 13 participants in two separate studies (ie. different equipment and sample background), cross-referencing and cross-validating the biological side of the protocol’s structure. Our findings suggest (a) that all participants—irrespectively of the study—reacted consistently in terms of hemispheric lateralization for each stimulus (ie. uniform intra-subjective emotional reaction; non-statistically-significant differentiation in individual variability) and (b) that diverse patterns of biological representations emerge for each stimulus between the subjects in the two studies (variable inter-subjective emotional reaction; statistically-significant differentiation in group variability) pointing towards exogenous to the measurements process factors. We conclude discussing further steps and implications of our protocol approach.
Studies of expertise have traditionally had a strong focus on the role of one single factor, i.e. long-term deliberate practice, for expert performance. However, recent empirical and theoretical work strongly suggests that expertise is a function of many variables that may have practice-independent effects on performance, but also moderate the efficacy of practice itself.
Here we study such interaction effects in a large cohort (n > 4,500) of Swedish twins, using music as a model domain, and measured expert performance (musical auditory discrimination) as well as self-reported real-life achievement as indices of expertise. Specifically, we test 2 recently proposed hypotheses, i.e. 1. that the efficacy of practice increases if the individual also takes part in teacher-led lessons, and 2. that practice efficacy increases with higher intelligence.
The results did not support the first hypothesis. Both practice and frequency of music lessons had positive associations with the 2 measures of expertise but, contrary to predictions, the interaction between them was negative, i.e. the effect of each practiced hour decreased with more lessons. In contrast, the second hypothesis was supported by the data, i.e. we found a positive interaction between practice and intelligence, suggesting that higher cognitive ability is related to more efficient practice behaviors.
Together the results further support that domain-specific expertise is a complex outcome, which depends on an interplay of a variety of factors.
Will Wilkinson explored one possibility in an essay he wrote a few years ago on American country music. Wilkinson begins with the observation that American conservatives (ie. the consumers of country music) tend to be low on “openness” in the Big-5 personality scale. Folks who rate high on openness are the sort attracted to novelty: world travels, new drugs, and so forth. Country music, he suggests, captures the emotional lives of a different group of people:
Emotional highlights of the low-openness life are going to be the type celebrated in “One Boy, One Girl”: the moment of falling in love with “the one”, the wedding day, the birth one’s children (though I guess the song is about a surprising ultrasound). More generally, country music comes again and again to the marvel of advancing through life’s stations, and finds delight in experiencing traditional familial and social relationships from both sides. Once I was a girl with a mother, now I’m a mother with a girl. My parents took care of me, and now I take care of them. I was once a teenage boy threatened by a girl’s gun-loving father, now I’m a gun-loving father threatening my girl’s teenage boy. Etc. And country is full of assurances that the pleasures of simple, rooted, small-town, lives of faith are deeper and more abiding than the alternatives.
My conjecture, then, is that country music functions in part to reinforce in low-openness individuals the idea that life’s most powerful, meaningful emotional experiences are precisely those to which conservative personalities living conventional lives are most likely to have access. And it functions as a device to coordinate members of conservative-minded communities on the incomparable emotional weight of traditional milestone experiences…
But why would you want your kids to grow up with the same way of life as you and your grandparents? My best guess (and let me stress guess) is that those low in openness depend emotionally on a sense of enchantment of the everyday and the profundity of ritual. Even a little change, like your kids playing with different toys than you did, comes as a small reminder of the instability of life over generations and the contingency of our emotional attachments. This is a reminder low-openness conservatives would prefer to avoid, if possible. What high-openness liberals feel as mere nostalgia, low-openness conservatives feel as the baseline emotional tone of a recognizably decent life. If your kids don’t experience the same meaningful things in the same way that you experienced them, then it may seem that their lives will be deprived of meaning, which would be tragic. And even if you’re able to see that your kids will find plenty of meaning, but in different things and in different ways, you might well worry about the possibility of ever really understanding and relating to them. The inability to bond over profound common experience would itself constitute a grave loss of meaning for both generations. So when the culture redefines a major life milestone, such as marriage, it trivializes one’s own milestone experience by imbuing it was a sense of contingency, threatens to deprive one’s children of the same experience, and thus threatens to make the generations strangers to one another. And what kind of monster would want that?
Country music is a bulwark against cultural change, a reminder that “what you see is what you get”, a means of keeping the charge of enchantment in “the little things” that make up the texture of the every day, and a way of literally broadcasting the emotional and cultural centrality of the conventional big-ticket experiences that make a life a life.3
…Yet there is one segment of society that seems to get it. In the years since my [Mormon missionary] service, I have been surprised to find that the one group of people who consistently understands my experience are soldiers…both many ex-missionaries (known as “RMs” or “Return Missionaries” in Mormon lingo) and many veterans have such trouble adapting to life when they return to their homes. This comparison occurred to me first several years ago, when I read a Facebook comment left by a man who had served as a Marine mechanic in Afghanistan…I did not save the comment at the time, but I remember it well enough to reproduce a paraphrase here:
“I do not know if I want to live any more. I served in Afghanistan from [various dates of various deployments] and am now working as a salesman for [a prominent American company]. I despise this world I am in now—everything is so selfish and so self centered. In Afghanistan every single decision I made had a purpose; every single thing I did was for something bigger than myself. Everything I did, I did to save lives. Every deed helped accomplish our mission. Here in America no one does anything except for themselves. We work to earn a buck—what is the point to living like this? There is not a day that goes by that I don’t wish I was back in that hellhole. There what I did mattered. Here it is all meaningless.”
Human symbol systems such as art and fashion styles emerge from complex social processes that govern the continuous re-organization of modern societies. They provide a signalling scheme that allows members of an elite to distinguish themselves from the rest of society.
Efforts to understand the dynamics of art and fashion cycles have been placed on ‘bottom-up’ and ‘top-down’ theories. According to ‘top-down’ theories, elite members signal their superior status by introducing new symbols (eg. fashion styles), which are adopted by low-status groups. In response to this adoption, elite members would need to introduce new symbols to signal their status. According to many ‘bottom-up’ theories, style cycles evolve from lower classes and follow an essentially random pattern. We propose an alternative explanation based on counter-dominance signalling (CDS). In CDS, elite members want others to imitate their symbols; changes only occur when outsider groups successfully challenge the elite by introducing signals that contrast those endorsed by the elite.
We investigate these mechanisms using a dynamic network approach on data containing almost 8 million music albums released between 1956 and 2015. The network systematically quantifies artistic similarities of competing musical styles and their changes over time. We formulate empirical tests for whether new symbols are introduced by current elite members (top-down), randomness (bottom-up) or by peripheral groups through counter-dominance signals. We find clear evidence that CDS drives changes in musical styles.
This provides a quantitative, completely data-driven answer to a century-old debate about the nature of the underlying social dynamics of fashion cycles.
[Keywords: cultural evolution, network analysis, evolutionary dynamics, fashion cycle theory]
Background music has been claimed to enhance people’s creativity. In three experiments, we investigated the impact of background music on performance of Compound Remote Associate Tasks (CRATs), which are widely thought to tap creativity. Background music with foreign (unfamiliar) lyrics (Experiment 1), instrumental music without lyrics (Experiment 2), and music with familiar lyrics (Experiment 3) all statistically-significantly impaired CRAT performance in comparison with quiet background conditions. Furthermore, Experiment 3 demonstrated that background music impaired CRAT performance regardless of whether the music induced a positive mood or whether participants typically studied in the presence of music. The findings challenge the view that background music enhances creativity and are discussed in terms of an auditory distraction account (interference-by-process) and the processing disfluency account.
We built a corpus of ethnographic text on musical behavior from a representative sample of the world’s societies, as well as a discography of audio recordings.
The ethnographic corpus reveals that music (including songs with words) appears in every society observed; that music varies along 3 dimensions (formality, arousal, religiosity), more within societies than across them; and that music is associated with certain behavioral contexts such as infant care, healing, dance, and love.
The discography-analyzed through machine summaries, amateur and expert listener ratings, and manual transcriptions-reveals that acoustic features of songs predict their primary behavioral context; that tonality is widespread, perhaps universal; that music varies in rhythmic and melodic complexity; and that elements of melodies and rhythms found worldwide follow power laws.
Music ranks among the greatest human pleasures. It consistently engages the reward system, and converging evidence implies it exploits predictions to do so. Both prediction confirmations and errors are essential for understanding one’s environment, and music offers many of each as it manipulates interacting patterns across multiple timescales. Learning models suggest that a balance of these outcomes (ie. intermediate complexity) optimizes the reduction of uncertainty to rewarding and pleasurable effect. Yet evidence of a similar pattern in music is mixed, hampered by arbitrary measures of complexity. In the present studies, we applied a well-validated information-theoretic model of auditory expectation to systematically measure two key aspects of musical complexity: predictability (operationalized as information content [IC]), and uncertainty (entropy). In Study 1, we evaluated how these properties affect musical preferences in 43 male and female participants; in Study 2, we replicated Study 1 in an independent sample of 27 people and assessed the contribution of veridical predictability by presenting the same stimuli seven times. Both studies revealed significant quadratic effects of IC and entropy on liking that outperformed linear effects, indicating reliable preferences for music of intermediate complexity. An interaction between IC and entropy further suggested preferences for more predictability during more uncertain contexts, which would facilitate uncertainty reduction. Repeating stimuli decreased liking ratings but did not disrupt the preference for intermediate complexity. Together, these findings support long-hypothesized optimal zones of predictability and uncertainty in musical pleasure with formal modeling, relating the pleasure of music listening to the intrinsic reward of learning.
Abstract pleasures, such as music, claim much of our time, energy, and money despite lacking any clear adaptive benefits like food or shelter. Yet as music manipulates patterns of melody, rhythm, and more, it proficiently exploits our expectations. Given the importance of anticipating and adapting to our ever-changing environments, making and evaluating uncertain predictions can have strong emotional effects. Accordingly, we present evidence that listeners consistently prefer music of intermediate predictive complexity, and that preferences shift toward expected musical outcomes in more uncertain contexts. These results are consistent with theories that emphasize the intrinsic reward of learning, both by updating inaccurate predictions and validating accurate ones, which is optimal in environments that present manageable predictive challenges (ie. reducible uncertainty).
Background: Recent studies indicate increased autistic traits in musicians with absolute pitch and a higher incidence of absolute pitch in people with autism. Theoretical accounts connect both of these with shared neural principles of local hyper-connectivity and global hypo-connectivity, enhanced perceptual functioning and a detail-focused cognitive style. This is the first study to investigate absolute pitch proficiency, autistic traits and brain correlates in the same study.
Sample and Methods: Graph theoretical analysis was conducted on resting state (eyes closed and eyes open) EEG connectivity (wPLI, weighted Phase Lag Index) matrices obtained from 31 absolute pitch (AP) and 33 relative pitch (RP) professional musicians. Small Worldness, Global Clustering Coefficient and Average Path length were related to autistic traits, passive (tone identification) and active (pitch adjustment) absolute pitch proficiency and onset of musical training using Welch-two-sample-tests, correlations and general linear models.
Results: Analyses revealed increased Path length (delta 2–4 Hz), reduced Clustering (beta 13–18 Hz), reduced Small-Worldness (gamma 30–60 Hz) and increased autistic traits for AP compared to RP. Only Clustering values (beta 13–18 Hz) were predicted by both AP proficiency and autistic traits. Post-hoc single connection permutation tests among raw wPLI matrices in the beta band (13–18 Hz) revealed widely reduced interhemispheric connectivity between bilateral auditory related electrode positions along with higher connectivity between F7-F8 and F8-P9 for AP. Pitch naming ability and Pitch adjustment ability were predicted by Path length, Clustering, autistic traits and onset of musical training (for pitch adjustment) explaining 44% respectively 38% of variance.
Conclusion: Results show both shared and distinct neural features between AP and autistic traits. Differences in the beta range were associated with higher autistic traits in the same population. In general, AP musicians exhibit a widely underconnected brain with reduced functional integration and reduced small-world-property during resting state. This might be partly related to autism-specific brain connectivity, while differences in Path length and Small-Worldness reflect other ability-specific influences. This is further evidence for different pathways in the acquisition and development of absolute pitch, likely influenced by both genetic and environmental factors and their interaction.
A meditation on subcultures & review of the cartoon series My Little Pony: Friendship Is Magic, focusing on fandom, plot, development, and meaning of bronydom.
I watch the 2010 Western animated series My Little Pony: Friendship is Magic (seasons 1–9), delving deep into it and the MLP fandom, and reflect on it. What makes it good and powers its fandom subculture, producing a wide array of fanfictions, music, and art? Focusing on fandom, plot, development, and meaning of bronydom, I conclude that, among other things, it has surprisingly high-quality production & aesthetics which are easily adapted to fandom and which power a Westernized shonen anime—which depicts an underappreciated plausibly-contemporary capitalist utopian perspective on self-actualization, reminiscent of other more explicitly self-help-oriented pop culture movements such as the recent Jordan B. Peterson movement. Included are my personal rankings of characters, seasons, episodes, and official & fan music.
Review of famous light novel series Umineko no Naku Koro ni: it is a highly idiosyncratic, wildly self-indulgent, yet impressive exploration of all possible locked-room mysteries, knocked for a loop mid-composition by personal tragedy, triggering a descent into a deeply harmful endorsement of fantasies & running from painful realities.
While writing my review, I took 2 geeky detours: estimating how much time, exactly, it had taken me to read through Umineko; and how long is Umineko compared to other works known for being incredibly long like Robert Jordan’s The Wheel of Time (which I have also read)?
Measuring the actual time spent reading, and comparing the compressed file sizes to normalize the formatting & repetition, Umineko is about as big as Shakespeare but still much smaller than the full Wheel of Time series.
Some people hear what they see: car indicator lights, flashing neon shop signs, and people’s movements as they walk may all trigger an auditory sensation, which we call the visual-evoked auditory response (vEAR or ‘visual ear’). We have conducted the first large-scale online survey (n > 4000) of this little-known phenomenon. We analysed the prevalence of vEAR, what induces it, and what other traits are associated with it.
We assessed prevalence by asking whether respondents had previously experienced vEAR. Participants then rated silent videos for vividness of evoked auditory sensations, and answered additional trait questions.
Prevalence appeared higher relative to other typical synaesthesias. Prior awareness and video ratings were associated with greater frequency of other synaesthesias, including flashes evoked by sounds, and musical imagery. Higher-rated videos often depicted meaningful events that predicted sounds (eg. collisions). However, even videos containing abstract flickering or moving patterns could also elicit higher ratings, despite having no predictable association with sounds. Such videos had higher levels of raw ‘motion energy’ (ME), which we quantified using a simple computational model of motion processing in early visual cortex. Critically, only respondents reporting prior awareness of vEAR tended to show a positive correlation between video ratings and ME.
This specific sensitivity to ME suggests that in vEAR, signals from visual motion processing may affect audition relatively directly without requiring higher-level interpretative processes. Our other findings challenge the popular assumption that individuals with synaesthesia are rare and have ideosyncratic patterns of brain hyper-connectivity. Instead, our findings of apparently high prevalence and broad associations with other synaesthesias and traits are jointly consistent with a common dependence on normal variations in physiological mechanisms of disinhibition or excitability of sensory brain areas and their functional connectivity. The prevalence of vEAR makes it easier to test such hypotheses further, and makes the results more relevant to understanding not only synaesthetic anomalies but also normal perception.
A suggested x-risk/Great Filter is the possibility of advanced entertainment technology leading to wireheading/mass sterility/population collapse and extinction. As media consumption patterns are highly heritable, any such effect would trigger rapid human adaptation, implying extinction is almost impossible unless immediate collapse or exponentially accelerating addictiveness.
To demonstrate the point that there are pervasive genetic influences on all aspects of media consumption or leisure time activities/preferences/attitudes, I compile >580 heritability estimates from the behavioral genetics literature (drawing particularly on Loehlin & Nichols 1976’s A Study of 850 Sets of Twins), roughly divided in ~13 categories.
A randomized experiment with almost 35 million Pandora listeners enables us to measure the sensitivity of consumers to advertising, an important topic of study in the era of ad-supported digital content provision. The experiment randomized listeners into 9 treatment groups, each of which received a different level of audio advertising interrupting their music listening, with the highest treatment group receiving more than twice as many ads as the lowest treatment group. By keeping consistent treatment assignment for 21 months, we are able to measure long-run demand effects, with three times as much ad-load sensitivity as we would have obtained if we had run a month-long experiment.
We estimate a demand curve that is strikingly linear, with the number of hours listened decreasing linearly in the number of ads per hour (also known as the price of ad-supported listening). We also show the negative impact on the number of days listened and on the probability of listening at all in the final month.
Using an experimental design that separately varies the number of commercial interruptions per hour and the number of ads per commercial interruption, we find that neither makes much difference to listeners beyond their impact on the total number of ads per hour. Lastly, we find that increased ad load causes a substantial increase in the number of paid ad-free subscriptions to Pandora, particularly among older listeners.
Research over the past decade has shown that various personality traits are communicated through musical preferences. One limitation of that research is external validity, as most studies have assessed individual differences in musical preferences using self-reports of music-genre preferences. Are personality traits communicated through behavioral manifestations of musical preferences? We addressed this question in two large-scale online studies with demographically diverse populations. Study 1 (n = 22,252) shows that reactions to unfamiliar musical excerpts predicted individual differences in personality—most notably, openness and extraversion—above and beyond demographic characteristics. Moreover, these personality traits were differentially associated with particular music-preference dimensions. The results from Study 2 (n = 21,929) replicated and extended these findings by showing that an active measure of naturally occurring behavior, Facebook Likes for musical artists, also predicted individual differences in personality. In general, our findings establish the robustness and external validity of the links between musical preferences and personality.
Instead of purchasing individual content, streaming adopters rent access to libraries from which they can consume content at no additional cost.
In this paper, we study how the adoption of music streaming affects listening behavior. Using a unique panel data set of individual consumers’ listening histories across many digital music platforms:
adoption of streaming leads to very large increases in the quantity and diversity of consumption in the first months after adoption. Although the effects attenuate over time, even after half a year, adopters play substantially more, and more diverse, music. Relative to music ownership, where experimentation is expensive, adoption of streaming increases new music discovery. While repeat listening to new music decreases, users’ best discoveries have higher play rates.
We discuss the implications for consumers and producers of music.
In this article, we propose a new explanation for why certain cultural products outperform their peers to achieve widespread success. We argue that products’ position in feature space significantly predicts their popular success.
Using tools from computer science, we construct a novel dataset allowing us to examine whether the musical features of nearly 27,000 songs from Billboard’s Hot 100 charts predict their levels of success in this cultural market. We find that, in addition to artist familiarity, genre affiliation, and institutional support, a song’s perceived proximity to its peers influences its position on the charts. Contrary to the claim that all popular music sounds the same, we find that songs sounding too much like previous and contemporaneous productions—those that are highly typical—are less likely to succeed. Songs exhibiting some degree of optimal differentiation are more likely to rise to the top of the charts.
These findings offer a new perspective on success in cultural markets by specifying how content organizes product competition and audience consumption behavior.
Music is increasingly used as an adjuvant for chronic pain management as it is not invasive, inexpensive, and patients usually report positive experiences with it. However, little is known about its clinical efficacy in chronic pain patients. In this systematic review and meta-analysis, we investigated randomized controlled trials (RCTs) of adult patients that reported any type of music intervention for chronic pain, chosen by the researcher or patient, lasting for any duration. Searches were performed using PsycINFO, Scopus and PubMed for RTCs published until the end of May 2016. The primary outcome was reduction in self-reported pain using a standardized pain measurement instrument reported post-intervention. The secondary outcomes were: quality of life measures, depression and anxiety measures, among others. The study was pre-registered with PROSPERO (CRD42016039837) and the meta-analysis was done using RevMan. We identified 768 titles and abstracts, and we included 14 RTCs that fulfilled our criteria. The sample size of the studies varied between 25 and 200 participants. We found that music reduced chronic pain, and depression, with higher effect size on pain and depression. We also found music had a higher effect when the participant chose the music in contrast with researcher-chosen music. The sample size of RCTs was small and sometimes with different outcome measures. Our analysis suggests that music may be beneficial as an adjuvant for chronic pain patients, as it reduces self-reported pain and its common co-morbidities. Importantly, the analgesic effect of music appears higher with self-chosen over researcher-chosen music.
Music training is thought to improve youngsters’ cognitive and academic skills.
Results show a small overall effect size (d = 0.16, K = 118).
Music training seems to moderately enhance youngsters’ intelligence and memory.
The design quality of the studies is negatively related to the size of the effects.
Future studies should include random assignment and active control groups.
Music training has been recently claimed to enhance children and young adolescents’ cognitive and academic skills. However, substantive research on transfer of skills suggests that far-transfer—ie. the transfer of skills between 2 areas only loosely related to each other—occurs rarely.
In this meta-analysis, we examined the available experimental evidence regarding the impact of music training on children and young adolescents’ cognitive and academic skills. The results of the random-effects models showed (a) a small overall effect size (d = 0.16); (b) slightly greater effect sizes with regard to intelligence (d = 0.35) and memory-related outcomes (d = 0.34); and (c) an inverse relation between the size of the effects and the methodological quality of the study design.
These results suggest that music training does not reliably enhance children and young adolescents’ cognitive or academic skills, and that previous positive findings were probably due to confounding variables.
[Keywords: music training, transfer, cognitive skills, education, meta-analysis]
Congenital amusia (commonly known as tone-deafness) is a lifelong musical disorder that should affect 4% of the population according to a single estimate based on a single test from 1980. Here we present the first large-based measure of prevalence with a sample of 20,000 participants that does not rely on self-referral. On the basis of three objective tests and a questionnaire, we show that (a) the prevalence of congenital amusia is only 1.5% with slightly more females than males, unlike other developmental disorders where males often predominate; (b) self-disclosure is a reliable index of congenital amusia, that suggests that congenital amusia is hereditary with 46% first-degree relatives similarly affected; (3) that the deficit is not attenuated by musical training and (4) it emerges in relative isolation from other cognitive disorder except for spatial orientation problems. Hence, we suggest that congenital amusia is likely to result from genetic variations that affect musical abilities specifically.
Although music is an universal feature of human culture, little is known about its origins and functions. A prominent theory of music evolution is the sexual selection hypothesis, which proposes that music evolved as a signal of genetic quality to potential mates. The sexual selection hypothesis offers several empirically testable predictions. First, musically skilled and active individuals should have greater mating success than less-skilled individuals. Second, if musical ability functions as an indicator of genetic quality, it is expected to be associated with other traits putatively related to genetic quality. Third, associations as per the first and second predictions are expected to be at least partly due to overlapping genetic influences. We tested these predictions in a large genetically informative sample of 10,975 Swedish twin individuals aged between 27 and 54 years (M = 40.1, SD = 7.7), using musical aptitude and music achievement as measures of musical ability. To assess mating success we examined number of sex-partners, age of first intercourse, sociosexuality, and number of offspring. General intelligence, simple reaction time, and height were used to investigate relationships with traits putatively related to genetic quality. Twin modeling showed moderate genetic influences on musical aptitude for both sexes (heritability estimates were 38% for males and 51% for females). Music achievement was also moderately influenced by genetic influences in males (heritability = 57%), but the genetic influences were low and nonsignificant for females (heritability = 9%). Contrary to predictions, the majority of phenotypic associations between musical ability and music achievement with mating success were nonsignificant or statistically-significant in the other direction, with those with greater musical ability scoring lower on the measures of mating success. Genetic correlations between these measures were also nonsignificant. Most correlations of musical aptitude and music achievement with genetic quality measures were statistically-significant, including correlations with general intelligence, simple reaction time, and, in females, height (but only for aptitude). However, only the correlation between musical aptitude and general intelligence in men was statistically-significantly driven by overlapping genetic influences. Our findings provide little support for a role of sexual selection in the evolution of musical ability. Alternative explanations and limitations are discussed.
[Discussion of the creation of modern sports training: professional athletes, even NBA stars, typically did not ‘train’. Practice was about getting into shape and working with teammates, if even that much—one simply took one’s skills for granted. Coaches focused on strategy, not coaching.
A harbinger of the professionalization of professional athletes was basketball player Kermit Washington, on the verge of washing out of the NBA early on until he swallowed his pride and began tutoring with coach Pete Newell, who drilled Kermit on the basics repeatedly. Kermit eventually became an All-Star player and influenced other NBA players to engage in coaching and deliberate practice to improve their fundamentals. The modern paradigm is a ruthless quest for perfection in every dimension, quantified, and applying the latest science and technology to eek out even the slightest fraction of a second improvement; athletes are projects, with many different specialists examining them constantly for potential improvements, and as importantly, when not to practice lest they be injured.
And the results speak for themselves—performance has never been higher, the impossible is now done routinely by many professionals, this continuous improvement trend has spread to other domains too, including chess, classical music, business. Equally striking are domains which don’t see trends like this, particular American education.]
“You need to have the best PhDs onboard as well”, McClusky says. This technological and analytical arms race is producing the best athletes in history.
The arms race centers on an obsessive scrutiny of every aspect of training and performance. Trainers today emphasize sports-specific training over generalized conditioning: if you’re a baseball player, you work on rotational power; if you’re a sprinter, on straight-line explosive power. All sorts of tools have been developed to improve vision, reaction time, and the like. The Dynavision D2 machine is a large board filled with flashing lights, which ballplayers have to slap while reading letters and math equations that the board displays. Football players use Nike’s Vapor Strobe goggles, which periodically cloud for tenth-of-a-second intervals, in order to train their eyes to focus even in the middle of chaos. Training is also increasingly personalized. Players are working not just with their own individual conditioning coaches but also with their own individual skills coaches. In non-team sports, such as tennis and golf, coaches were rare until the seventies. Today, tennis players such as Novak Djokovic have not just a single coach but an entire entourage. In team sports, meanwhile, there’s been a proliferation of gurus. George Whitfield has built a career as a “quarterback whisperer”, turning college quarterbacks into NFL-ready prospects. Ron Wolforth, a pitching coach, is known for resurrecting pitchers’ careers—he recently transformed the Oakland A’s Scott Kazmir from a has-been into an All-Star by revamping his mechanics and motion. Then there’s the increasing use of biometric sensors, equipped with heart-rate monitors, G.P.S., and gyroscopes, to measure not just performance (how fast a player is accelerating or cutting) but also fatigue levels. And since many studies show that getting more sleep leads to better performance, teams are now worrying about that, too. The N.B.A.’s Dallas Mavericks have equipped players with Readiband monitors to measure how much, and how well, they’re sleeping.
All this effort may sound a bit nuts. But it’s how you end up with someone like Chris Hoy, the British cyclist who won two gold medals at the London Olympics in 2012, trailed by a team of scientists, nutritionists, and engineers. Hoy ate a carefully designed diet of five thousand calories a day. His daily workouts—two hours of lifting in the morning, three hours in the velodrome in the afternoon, and an easy one-hour recovery ride in the evening—had been crafted to maximize both his explosive power and his endurance. He had practiced in wind tunnels at the University of Southampton. He had worn biofeedback sensors that delivered exact data to his trainers about how his body was responding to practice. The eighty-thousand-dollar carbon-fibre bike he rode helped, too. Hoy was the ultimate product of an elaborate and finely tuned system designed to create the best cyclist possible. And—since his competitors weren’t slacking, either—he still won by only a fraction of a second.
The relative importance of nature and nurture for various forms of expertise has been intensely debated. Music proficiency is viewed as a general model for expertise, and associations between deliberate practice and music proficiency have been interpreted as supporting the prevailing idea that long-term deliberate practice inevitably results in increased music ability.
Here, we examined the associations (rs = 0.18–0.36) between music practice and music ability (rhythm, melody, and pitch discrimination) in 10,500 Swedish twins. We found that music practice was substantially heritable (40%–70%). Associations between music practice and music ability were predominantly genetic, and, contrary to the causal hypothesis, nonshared environmental influences did not contribute. There was no difference in ability within monozygotic twin pairs differing in their amount of practice, so that when genetic predisposition was controlled for, more practice was no longer associated with better music skills.
These findings suggest that music practice may not causally influence music ability and that genetic variation among individuals affects both ability and inclination to practice.
[Keywords: training, expertise, music ability, practice, heritability, twin, causality]
Ericsson and colleagues argue that deliberate practice explains expert performance.
We tested this view in the two most studied domains in expertise research.
Deliberate practice is not sufficient to explain expert performance.
Other factors must be considered to advance the science of expertise.
Twenty years ago, Ericsson et al 1993 proposed that expert performance reflects a long period of deliberate practice rather than innate ability, or “talent”. Ericsson et al 1993 found that elite musicians had accumulated thousands of hours more deliberate practice than less accomplished musicians, and concluded that their theoretical framework could provide “a sufficient account of the major facts about the nature and scarcity of exceptional performance” (p. 392). The deliberate practice view has since gained popularity as a theoretical account of expert performance, but here we show that deliberate practice is not sufficient to explain individual differences in performance in the two most widely studied domains in expertise research—chess and music. For researchers interested in advancing the science of expert performance, the task now is to develop and rigorously test theories that take into account as many potentially relevant explanatory constructs as possible.
Music is among all cultures an important part of the lives of most people. Music has psychological benefits and may generate strong emotional and physiological responses. Recently, neuroscientists have discovered that music influences the reward circuit of the nucleus accumbens (NAcc), even when no explicit reward is present.
In this clinical case study, we describe a 60-year old patient who developed a sudden and distinct musical preference for Johnny Cash following deep brain stimulation (DBS) targeted at the NAcc.
This case report substantiates the assumption that the NAcc is involved in musical preference, based on the observation of direct stimulation of the accumbens with DBS. It also shows that accumbens DBS can change musical preference without habituation of its rewarding properties.
Music is an integral part of the cultural heritage of all known human societies, with the capacity for music perception and production present in most people. Researchers generally agree that both genetic and environmental factors contribute to the broader realization of music ability, with the degree of music aptitude varying, not only from individual to individual, but across various components of music ability within the same individual.
While environmental factors influencing music development and expertise have been well investigated in the psychological and music literature, the interrogation of possible genetic influences has not progressed at the same rate. Recent advances in genetic research offer fertile ground for exploring the genetic basis of music ability. This paper begins with a brief overview of behavioral and molecular genetic approaches commonly used in human genetic analyses, and then critically reviews the key findings of genetic investigations of the components of music ability. Some promising and converging findings have emerged, with several loci on chromosome 4 implicated in singing and music perception, and certain loci on chromosome 8q implicated in absolute pitch and music perception. The gene AVPR1A on chromosome 12q has also been implicated in music perception, music memory, and music listening, whereas SLC6A4 on chromosome 17q has been associated with music memory and choir participation. Replication of these results in alternate populations and with larger samples is warranted to confirm the findings.
Through increased research efforts, a clearer picture of the genetic mechanisms underpinning music ability will hopefully emerge.
Theories of skilled performance that emphasize training history, such as K. Anders Ericsson and colleagues’ deliberate-practice theory, have received a great deal of recent attention in both the scientific literature and the popular press. Twin studies, however, have demonstrated evidence for moderate-to-strong genetic influences on skilled performance.
Focusing on musical accomplishment in a sample of over 800 pairs of twins, we found evidence for gene-environment correlation, in the form of a genetic effect on music practice. However, only about one quarter of the genetic effect on music accomplishment was explained by this genetic effect on music practice, suggesting that genetically influenced factors other than practice contribute to individual differences in music accomplishment.
We also found evidence for gene-environment interaction, such that genetic effects on music accomplishment were most pronounced among those engaging in music practice, suggesting that genetic potentials for skilled performance are most fully expressed and fostered by practice.
Young children regularly engage in musical activities, but the effects of early music education on children’s cognitive development are unknown. While some studies have found associations between musical training in childhood and later nonmusical cognitive outcomes, few randomized controlled trials (RCTs) have been employed to assess causal effects of music lessons on child cognition and no clear pattern of results has emerged. We conducted two RCTs with preschool children investigating the cognitive effects of a brief series of music classes, as compared to a similar but non-musical form of arts instruction (visual arts classes, Experiment (1) or to a no-treatment control (Experiment (2). Consistent with typical preschool arts enrichment programs, parents attended classes with their children, participating in a variety of developmentally appropriate arts activities. After six weeks of class, we assessed children’s skills in four distinct cognitive areas in which older arts-trained students have been reported to excel: spatial-navigational reasoning, visual form analysis, numerical discrimination, and receptive vocabulary. We initially found that children from the music class showed greater spatial-navigational ability than did children from the visual arts class, while children from the visual arts class showed greater visual form analysis ability than children from the music class (Experiment 1). However, a partial replication attempt comparing music training to a no-treatment control failed to confirm these findings (Experiment (2), and the combined results of the two experiments were negative: overall, children provided with music classes performed no better than those with visual arts or no classes on any assessment. Our findings underscore the need for replication in RCTs, and suggest caution in interpreting the positive findings from past studies of cognitive effects of music instruction.
This study examined the college entrance examination scores of music and non-music students in the United States, drawing data from the restricted-use data set of the Education Longitudinal Study of 2002 (ELS), a nationally representative education study (n = 15,630) conducted by the National Center for Education Statistics. Analyses of high school transcript data from ELS showed that 1.127 million students (36.38% of the U.S. class of 2004) graduated high school having earned at least one course credit in music. Fixed-effects regression procedures were used to compare standardized test scores of these music students to their non-music peers while controlling for variables from the domains of demography, prior academic achievement, time use, and attitudes toward school. Results indicated that music students did not outperform non-music students on the SAT once these systematic differences had been statistically controlled. The obtained pattern of results remained consistent and robust through internal replications with another standardized math test and when disaggregating music students by type of music studied.
Essay by Pop Art artist Takashi Murakami on Japanese society and on WWII infantilizing Japanese culture as revealed by media, anime, and otaku.
“Earth In My Window” is a long essay by Superflat pop artist Takashi Murakami meditating on post-WWII consumerist Japanese society and on WWII infantilizing Japanese pop culture as revealed by its influences on media, anime, and the otaku subculture.
Since a 1997 review by Karageorghis and Terry, which highlighted the state of knowledge and methodological weaknesses, the number of studies investigating musical reactivity in relation to exercise has swelled considerably. In this two-part review paper, the development of conceptual approaches and mechanisms underlying the effects of music are explicated (Part I), followed by a critical review and synthesis of empirical work (spread over Parts I and II).
Pre-task music has been shown to optimize arousal, facilitate task-relevant imagery and improve performance in simple motoric tasks. During repetitive, endurance-type activities, self-selected, motivational and stimulative music has been shown to enhance affect, reduce ratings of perceived exertion, improve energy efficiency and lead to increased work output. There is evidence to suggest that carefully selected music can promote ergogenic and psychological benefits during high-intensity exercise, although it appears to be ineffective in reducing perceptions of exertion beyond the anaerobic threshold. The effects of music appear to be at their most potent when it is used to accompany self-paced exercise or in externally valid conditions. When selected according to its motivational qualities, the positive impact of music on both psychological state and performance is magnified. Guidelines are provided for future research and exercise practitioners.
Since a 1997 review by Karageorghis and Terry, which highlighted the state of knowledge and methodological weaknesses, the number of studies investigating musical reactivity in relation to exercise has swelled considerably. In this two-part review paper, the development of conceptual approaches and mechanisms underlying the effects of music are explicated (Part I), followed by a critical review and synthesis of empirical work (spread over Parts I and II).
Pre-task music has been shown to optimize arousal, facilitate task-relevant imagery and improve performance in simple motoric tasks. During repetitive, endurance-type activities, self-selected, motivational and stimulative music has been shown to enhance affect, reduce ratings of perceived exertion, improve energy efficiency and lead to increased work output. There is evidence to suggest that carefully selected music can promote ergogenic and psychological benefits during high-intensity exercise, although it appears to be ineffective in reducing perceptions of exertion beyond the anaerobic threshold. The effects of music appear to be at their most potent when it is used to accompany self-paced exercise or in externally valid conditions. When selected according to its motivational qualities, the positive impact of music on both psychological state and performance is magnified. Guidelines are provided for future research and exercise practitioners.
Director Anno Hideaki’s series Neon Genesis Evangelion caused a sensation when it first aired on TV Tokyo in 1995 and has become one of the most influential anime ever made. Since its premiere, fans across the globe have debated the possible interpretations of the complex plot, but little has been said about how composer Sagisu Shiro’s score might contribute to understanding the series. Anno’s rehabilitation in a Jungian clinic and subsequent personal study of human psychology plays heavily into understanding the main character Ikari Shinji, and music has much to contribute to appreciating Shinji’s view of the world. Shinji is an impressionable fourteen-year old boy, so his musical interpretations of the people and things around him do not always match reality. Sagisu’s music gives the viewers welcome insight into Shinji’s thoughts and feelings as he matures throughout the series.
We use neuroimaging to predict cultural popularity—something that is popular in the broadest sense and appeals to a large number of individuals.
Neuroeconomic research suggests that activity in reward-related regions of the brain, notably the orbitofrontal cortex and ventral striatum, is predictive of future purchasing decisions, but it is unknown whether the neural signals of a small group of individuals are predictive of the purchasing decisions of the population at large. For neuroimaging to be useful as a measure of widespread popularity, these neural responses would have to generalize to a much larger population that is not the direct subject of the brain imaging itself.
Here, we test the possibility of using functional magnetic resonance imaging (fMRI) to predict the relative popularity of a common good: music. We used fMRI to measure the brain responses of a relatively small [n = 27] group of adolescents while listening to [k = 20] songs of largely unknown artists. As a measure of popularity, the sales of these songs were totaled for the 3 years following scanning, and brain responses were then correlated with these “future” earnings.
Although subjective likability of the songs was not predictive of sales, activity within the ventral striatum was statistically-significantly correlated with the number of units sold.
These results suggest that the neural responses to goods are not only predictive of purchase decisions for those individuals actually scanned, but such responses generalize to the population at large and may be used to predict cultural popularity.
The advent of file sharing has considerably weakened effective copyright protection. Today, more than 60% of Internet traffic consists of consumers sharing music, movies, books, and games. Yet, despite the popularity of the new technology, file sharing has not undermined the incentives of authors to produce new works. We argue that the effect of file sharing has been muted for three reasons. (1) The cannibalization of sales that is due to file sharing is more modest than many observers assume. Empirical work suggests that in music, no more than 20% of the recent decline in sales is due to sharing. (2) File sharing increases the demand for complements to protected works, raising, for instance, the demand for concerts and concert prices. The sale of more expensive complements has added to artists’ incomes. (3) In many creative industries, monetary incentives play a reduced role in motivating authors to remain creative. Data on the supply of new works are consistent with the argument that file sharing did not discourage authors and publishers. Since the advent of file sharing, the production of music, books, and movies has increased sharply.
Artistic creativity forms the basis of music culture and music industry. Composing, improvising and arranging music are complex creative functions of the human brain, which biological value remains unknown. We hypothesized that practicing music is social communication that needs musical aptitude and even creativity in music. In order to understand the neurobiological basis of music in human evolution and communication we analyzed polymorphisms of the arginine vasopressin receptor 1A (AVPR1A), serotonin transporter (SLC6A4), catecol-O-methyltranferase (COMT), dopamine receptor D2 (DRD2) and tyrosine hydroxylase 1 (TPH1), genes associated with social bonding and cognitive functions in 19 Finnish families (n = 343 members) with professional musicians and/or active amateurs. All family members were tested for musical aptitude using the auditory structuring ability test (Karma Music test; KMT) and Carl Seashores tests for pitch (SP) and for time (ST). Data on creativity in music (composing, improvising and/or arranging music) was surveyed using a web-based questionnaire. Here we show for the first time that creative functions in music have a strong genetic component (h2 = 0.84; composing h2 = 0.40; arranging h2 = 0.46; improvising h2 = 0.62) in Finnish multigenerational families. We also show that high music test scores are statistically-significantly associated with creative functions in music (p < 0.0001). We discovered an overall haplotype association with AVPR1A gene (markers RS1 and RS3) and KMT (p = 0.0008; corrected p = 0.00002), SP (p = 0.0261; corrected p = 0.0072) and combined music test scores (COMB) (p = 0.0056; corrected p = 0.0006). AVPR1A haplotype AVR+RS1 further suggested a positive association with ST (p = 0.0038; corrected p = 0.00184) and COMB (p = 0.0083; corrected p = 0.0040) using haplotype-based association test HBAT. The results suggest that the neurobiology of music perception and production is likely to be related to the pathways affecting intrinsic attachment behavior.
[Note that the candidate-gene hits here are highly dubious.]
Synaesthesia is a benign neurological condition in humans characterized by involuntary cross-activation of the senses, and estimated to affect at least 1% of the population. Multiple forms of synaesthesia exist, including distinct visual, tactile or gustatory perceptions which are automatically triggered by a stimulus with different sensory properties, such as seeing colors when hearing music.
Surprisingly, there has been no previous report of synaesthetic sound perception. Here we report that auditory synaesthesia does indeed exist with evidence from 4 healthy adults for whom seeing visual flashes or visual motion automatically causes the perception of sound. As an objective test, we show that ‘hearing-motion synesthetes’ outperformed normal control subjects on an otherwise difficult visual task involving rhythmic temporal patterns similar to Morse code. Synesthetes had an advantage because they not could not only see, but also hear the rhythmic visual patterns.
Hearing-motion synaesthesia could be an useful tool for studying how the auditory and visual processing systems interact in the brain.
Individuals influence each others’ decisions about cultural products such as songs, books, and movies; but to what extent can the perception of success become a “self-fulfilling prophecy”? We have explored this question experimentally by artificially inverting the true popularity of songs in an online “music market”, in which 12,207 participants listened to and downloaded songs by unknown bands. We found that most songs experienced self-fulfilling prophecies, in which perceived-but initially false-popularity became real over time. We also found, however, that the inversion was not self-fulfilling for the market as a whole, in part because the very best songs recovered their popularity in the long run. Moreover, the distortion of market information reduced the correlation between appeal and popularity, and led to fewer overall downloads. These results, although partial and speculative, suggest a new approach to the study of cultural markets, and indicate the potential of web-based experiments to explore the social psychological origin of other macro-sociological phenomena.
The relationship between musical training and general intellectual capacity as well as academic achievement has been discussed in numerous contexts.
In our study, we examined the relationship between participation and achievement in music and achievement in academic courses, based on data from 3 consecutive British Columbia student cohorts.
Across the 3 cohorts, we consistently found that music participation was associated with generally higher academic achievement, and that Grade 11 music course scores predicted Grade 12 academic achievement scores in linear regression analyses.
Our results support the notion that the time dedicated to music participation does not impede, but rather goes hand in hand with or even fosters academic excellence in other ‘core’ subjects.
[Super-confounded, of course, and randomized musical training does not do anything.]
This study of the effects of three years of piano instruction is based on a sample of 117 fourth-grade children attending public schools in Montreal. The children had never participated in formal music instruction, did not have a piano at home, and their annual family income was below $40,000 Can. Children in the experimental group (n = 63) received individual piano lessons weekly for three years and were given an acoustic piano at no cost to their families. Children in the control group (n = 54) did not participate in formal music instruction. Participants were administered tests of self-esteem, academic achievement, cognitive abilities, musical abilities, and motor proficiency at the beginning of the project and throughout the three years of piano instruction. The results indicated that piano instruction had a positive effect on children’s self-esteem and school music marks but did not affect their academic achievement in math and language as measured by standardized tests and school report cards.
The continuing controversy over online file sharing sparks me to offer a few thoughts as an author and publisher. To be sure, I write and publish neither movies nor music, but books. But I think that some of the lessons of my experience still apply.
Lesson 1: Obscurity is a far greater threat to authors and creative artists than piracy.
…More than 100,000 books are published each year, with several million books in print, yet fewer than 10,000 of those new books have any substantial sales, and only a hundred thousand or so of all the books in print are carried in even the largest stores…The web has been a boon for readers, since it makes it easier to spread book recommendations and to purchase the books once you hear about them. But even then, few books survive their first year or two in print. Empty the warehouses and you couldn’t give many of them away…
Lesson 2: Piracy is progressive taxation
For all of these creative artists, most laboring in obscurity, being well-enough known to be pirated would be a crowning achievement. Piracy is a kind of progressive taxation, which may shave a few percentage points off the sales of well-known artists (and I say “may” because even that point is not proven), in exchange for massive benefits to the far greater number for whom exposure may lead to increased revenues…
Lesson 3: Customers want to do the right thing, if they can.
…We’ve found little or no abatement of sales of printed books that are also available for sale online…The simplest way to get customers to stop trading illicit digital copies of music and movies is to give those customers a legitimate alternative, at a fair price.
Lesson 4: Shoplifting is a bigger threat than piracy.
…What we have is a problem that is analogous, at best, to shoplifting, an annoying cost of doing business. And overall, as a book publisher who also makes many of our books available in electronic form, we rate the piracy problem as somewhere below shoplifting as a tax on our revenues. Consistent with my observation that obscurity is a greater danger than piracy, shoplifting of a single copy can lead to lost sales of many more. If a bookstore has only one copy of your book, or a music store one copy of your CD, a shoplifted copy essentially makes it disappear from the next potential buyer’s field of possibility. Because the store’s inventory control system says the product hasn’t been sold, it may not be reordered for weeks or months, perhaps not at all. I have many times asked a bookstore why they didn’t have copies of one of my books, only to be told, after a quick look at the inventory control system: “But we do. It says we still have one copy in stock, and it hasn’t sold in months, so we see no need to reorder.” It takes some prodding to force the point that perhaps it hasn’t sold because it is no longer on the shelf…
Lesson 5: File sharing networks don’t threaten book, music, or film publishing. They threaten existing publishers.
…The question before us is not whether technologies such as peer-to-peer file sharing will undermine the role of the creative artist or the publisher, but how creative artists can leverage new technologies to increase the visibility of their work. For publishers, the question is whether they will understand how to perform their role in the new medium before someone else does. Publishing is an ecological niche; new publishers will rush in to fill it if the old ones fail to do so…Over time, it may be that online music publishing services will replace CDs and other physical distribution media, much as recorded music relegated sheet music publishers to a niche and, for many, made household pianos a nostalgic affectation rather than the home entertainment center. But the role of the artist and the music publisher will remain. The question then, is not the death of book publishing, music publishing, or film production, but rather one of who will be the publishers.
Lesson 6: “Free” is eventually replaced by a higher-quality paid service
A question for my readers: How many of you still get your email via peer-to-peer UUCP dialups or the old “free” Internet, and how many of you pay $32.67$19.952002 a month or more to an ISP? How many of you watch “free” television over the airwaves, and how many of you pay $32.8$20.02002–$98.3$60.02002 a month for cable or satellite television? (Not to mention continue to rent movies on videotape and DVD, and purchasing physical copies of your favorites.) Services like Kazaa flourish in the absence of competitive alternatives. I confidently predict that once the music industry provides a service that provides access to all the same songs, freedom from onerous copy-restriction, more accurate metadata and other added value, there will be hundreds of millions of paying subscribers…Another lesson from television is that people prefer subscriptions to pay-per-view, except for very special events. What’s more, they prefer subscriptions to larger collections of content, rather than single channels. So, people subscribe to “the movie package”, “the sports package” and so on. The recording industry’s “per song” trial balloons may work, but I predict that in the long term, an “all-you-can-eat” monthly subscription service (perhaps segmented by musical genre) will prevail in the marketplace.
Lesson 7: There’s more than one way to do it.
A study of other media marketplaces shows, though, that there is no single silver-bullet solution. A smart company maximizes revenue through all its channels, realizing that its real opportunity comes when it serves the customer who ultimately pays its bills…Interestingly, some of our most successful print/online hybrids have come about where we present the same material in different ways for the print and online contexts. For example, much of the content of our bestselling book Programming Perl (more than 600,000 copies in print) is available online as part of the standard Perl documentation. But the entire package—not to mention the convenience of a paper copy, and the aesthetic pleasure of the strongly branded packaging—is only available in print. Multiple ways to present the same information and the same product increase the overall size and richness of the market. And that’s the ultimate lesson. “Give the Wookiee what he wants!” as Han Solo said so memorably in the first Star Wars movie. Give it to him in as many ways as you can find, at a fair price, and let him choose which works best for him.
The optimal complexity and preference-feedback hypotheses make specific predictions about the effects of stimulus familiarity and subjective complexity on liking for music excerpts.
This study investigated the relationships between each of these 3 variables within the same experimental design. 75 undergraduates rated 60 excerpts of contemporary popular music for liking, subjective complexity, or familiarity.
Results: strongly supported the predictions of the 2 models, indicating a positive relationship between liking and familiarity, and an inverted-U relationship between liking and subjective complexity.
The observed relationship between familiarity and subjective complexity was more difficult to predict and explain, although there was some evidence that this relationship might best be described as an inverted-U function. The different relationships of these 2 variables with liking are explained in terms of subjective complexity being related to objective properties of the stimuli, and familiarity being determined by cultural exposure and subjects’ own volition.
Subjects aged 4–5 yrs, 6–7 yrs, 8–9 yrs, 10–11 yrs, 13–14 yrs, and 18 yrs or older (n = 16 per group) were asked to rate 5 tone sequences in each of 4 categories: familiar or unfamiliar melodies and near or far approximations to music.
Data show that familiar melodies were best liked, followed by unfamiliar melodies, near approximations, and far approximations. There was an overall decline in liking for the stimuli with age.
…In summary, liking ratings for familiar and unfamiliar real-life melodies were obtained which were consistent with the hypothesized inverted-U relationship between liking and familiarity, with age representing the latter. The results were consistent with the hypothesis that the peak of the inverted U would occur at a later age for unfamiliar than for familiar melodies. The pattern of ratings obtained for the statistical approximations to music was also consistent with the inverted-U hypothesis: liking was an inverse function of age for these stimuli, and it was argued that this was because the extent to which they appeared unfamiliar when compared with the other melodies increased with age. No difference was found between ratings given to the 2 types of statistical approximation to music. In general terms, these results provide further support for the “optimum complexity” model of musical preference.
An inverted-U theory of the relationship between the subjective complexity of and liking for different musical pieces was developed. The theory was then used to derive some predictions about the effects of repetition on liking for pieces of music of different styles chosen to represent contrasting levels of objective complexity. These predictions were tested in two experiments. The first experiment was a short time-scale study in which two pieces (“easy-listening” music and avant-garde jazz) were played to subjects three times during a single session. The second experiment involved repetition over 3 weekly sessions, as well as four times within sessions, of three pieces (popular, classical, and avant-garde jazz). The results of both experiments were interpreted as broadly supporting the inverted-U model although there were some surprising exceptions. These exceptions occurred when functions relating familiarity and liking were compared between musical styles, and they were tentatively explained in terms of attitudinal stereotyping.
Much of the so-called new experimental aesthetics is concerned with liking as a function of novelty/familiarity.
The mere-exposure hypothesis, suggesting that liking is the result of ‘mere repeated exposure’ of the individual to the stimulus, is critically discussed.
The view is then considered that, more generally, the relationship between novelty/familiarity and liking takes the form of an inverted U. Theories purporting to explain this relationship are then briefly described. Next, our own experiments on letters, words and surnames, which show results consistent with the inverted-U function are reported.
However, for a certain category of stimuli, where the preference-feedback effect is in evidence, the relationship between novelty/familiarity and liking is more like a positive rectilinear one. This is well illustrated by our findings concerning preferences for Christian names.
This brings us to the topic of vogues. A survey of studies of aesthetic appreciation of music highlights, among other features, the presence of cycles of fashion of varying periodicities.
The chapter ends up with some tentative general conclusions about aesthetic preferences in relation to novelty.
The authors discuss special features of their studies of human likes and dislikes, summarize previous findings, and outline new perspectives in experimental aesthetics.
Previous research has emphasized the relationship between the familiarity of objects and people’s liking for them. A design feature that distinguishes the author’s work from other studies is the use of subjective, rather than objective, measures of familiarity.
Studies reviewed include those concerning letters, syllables, and words; names and preference feedback; and appreciation of music.
Probably the first sustained attempt to explore the value of music as therapy was made by a group of psychiatrists at the Walter Reed Hospital, during World War II, under the stimulus of the large number of psychiatric casualties requiring treatment. This first pragmatic approach has fortunately been developed into a more permanent research organization by one of the participants, Miss Paperte, in her creation of the Music Research Foundation. The present article proposes to review very briefly the nascent research in this area and to set out the results of a 3-year research project supported partly by the Music Research Foundation and partly by the Graduate School of the University of Illinois.
…The aim of the research report in this and 2 succeeding articles9, 10, sustained partly by the author’s own research resources and partly by the Bonfils Fellowship and other assistance from the Musical Research Foundation, has been to investigate relations between musical choice and personality, in normal and pathological subjects. Secondarily, it aims to produce a music choice test for personality diagnosis11.
…A preliminary list of 200 musical excerpts, from different periods, countries, and styles was tried out with about 50 students and was cut down to 120 by eliminating any piece which seemed very similar to any other or which for some peculiar reason of instrument or period was deemed likely to be unreliable. We then arranged for a skilled pianist to record the 120 excerpts on piano, since we wished to eliminate any chance effects which might be due to cultural attachments of the subjects to particular instruments.
…Factorization of like and dislike reactions to 120 musical excerpts by a population of 196 “normal” men and women in early maturity has yielded 12 factors, 8 of which are confirmed by 2 independent rotations of the material, one more moderately confirmed, and 3 awaiting further research.
Although the definition and soundness of simple structure for these factors is of a high order, little attempt has been made here to infer their nature from the particular association of musical likes and dislikes connected with them, though in some cases “hunches” indicated by the data are mentioned. Our general hypothesis that these independent dimensions of choice will turn out to be personality and temperament factors rather than patterns of specific musical content or school seems sufficiently sustained.
Research leading to more extensive interpretation of the psychological meaning of the factors should be possible now that I.P.A.T. has made the above excerpts available on a single, 12 ins. long-playing record11. Our own interpretations will wait on our use of this instrument in research directed to relating these factors to measured personality factors and pathological syndromes.
