JDS Journal of Data Science 1683-86021680-743X1680-743X School of Statistics, Renmin University of China JDS1040 10.6339/22-JDS1040 Data Science in Action What Kind of Music Do You Like? A Statistical Analysis of Music Genre Popularity Over Time PetitbonAimée M.apetitbon@gmail.com1∗ HitchcockDavid B.1 Department of Statistics, University of South Carolina, Columbia, SC 29208, USA Corresponding author. Email: apetitbon@gmail.com. 20222042022202168187 Supplementary Material

This includes the raw data files for both Hot 100 and Pazz & Jop listing singles and albums and genre assignments and all R code used in our analysis along with an explanatory README.txt file. Other items include: Full tables of genre counts for years 1974-2018; Tables of estimated multinomial logit model coefficients; Scatterplot matrix of candidate predictors; Various residual plots; Diagnostic plots for association analysis; Boxplots of 2019 Hot 100 forecasts from the model with the cubic time trend; and the cross-correlation function graph.

9122021632022 2022 The Author(s). Published by the School of Statistics and the Center for Applied Statistics, Renmin University of China.2022 Open access article under the CC BY license.

Popular music genre preferences can be measured by consumer sales, listening habits, and critics’ opinions. We analyze trends in genre preferences from 1974 through 2018 presented in annual Billboard Hot 100 charts and annual Village Voice Pazz & Jop critics’ polls. We model yearly counts of appearances in these lists for eight music genres with two multinomial logit models, using various demographic, social, and industry variables as predictors. Since the counts are correlated over time, we use a partial likelihood approach to fit the models. Our models provide strong fits to the observed genre proportions and illuminate trends in the popularity of genres over the sampled years, such as the rise of country music and the decline of rock music in consumer preferences, and the rise of rap/hip-hop in popularity among both consumers and critics. We forecast the genre proportions (for consumers and critics) for 2019 using fitted multinomial probabilities constructed from forecasts of 2019 predictor values and compare our Hot 100 forecasts to observed 2019 Hot 100 proportions. We model over time the association between consumer and critics’ preferences using Cramér’s measure of association between nominal variables and forecast how this association might trend in the future.

 baseline-category logit consumer preferences Cramér’s V forecasting multinomial logit model partial likelihood References Agresti A (2015). Foundations of Linear and Generalized Linear Models. John Wiley & Sons. Akaike H (1973). Information theory and an extension of the maximum likelihood principle. In: Second International Symposium on Information Theory (BN Petrov, F Csáki, eds.), 267–281. Akadémiai Kiadó, Budapest. Andrews C, Gardiner K, Jain TK, Olomi Y, North AC (2020). Culture, personal values, personality, uses of music, and musical taste. Psychology of Aesthetics, Creativity, and the Arts. Advance online publication. Beckwith J (2016). The evolution of music genre popularity. The DataFace. Online at https://thedataface.com/2016/09/culture/genre-lifecycles. Posted September 7, 2016. Accessed July 8, 2021. Bogdanov V, Woodstra C, Erlewine ST (2002). All Music Guide to Rock: the Definitive Guide to Rock, Pop, and Soul. Hal Leonard Corporation. Bradlow ET, Fader PS (2001). A Bayesian lifetime model for the “Hot 100” Billboard songs. Journal of the American Statistical Association, 96(454): 368–381. Breslow NE, Clayton DG (1993). Approximate inference in generalized linear mixed models. Journal of the American Statistical Association, 88(421): 9–25. Bryson B (1996). “Anything but heavy metal”: Symbolic exclusion and musical dislikes. American Sociological Review, 884–899. Chan KS, Ripley B (2020). TSA: Time Series Analysis. R package version 1.3. Coinnews Media Group LLC, (2021). Historical inflation rates, 1914-2021. https://www.usinflationcalculator.com/inflation/historical-inflation-rates Condylios S (2020). priceR: Economics and Pricing Tools. R package version 0.1.5. Cramér H (1945). Mathematical Methods of Statistics. Univ. Press, Princeton, NJ. Crawford S (2021). Facebook’s Village Voice Pazz & Jop Rip off Poll 2020, reviewed. Rock NYC. Online at http://rocknyc.live/facebooks-village-voice-pazz-and-jop-rip-off-poll-2020-reviewed.html. Posted January 4, 2021. Accessed February 3, 2022. Crawford S (2022). Village Voice Pazz and Jop Ripoff Poll 2021. Rock NYC. Online at https://rocknyc.live/village-voice-pazz-and-jop-ripoff-poll-2021.html. Posted January 16, 2022. Accessed February 3, 2022. Fokianos K, Kedem B (2004). Partial likelihood inference for time series following generalized linear models. Journal of Time Series Analysis, 25(2): 173–197. Greenberg DM, Baron-Cohen S, Stillwell DJ, Kosinski M, Rentfrow PJ (2015). Musical preferences are linked to cognitive styles. PloS One, 10(7): e0131151. GSS Data Explorer (2021). Think of self as liberal or conservative. https://gssdataexplorer.norc.org/variables/178/vshow. Harvilla R (2017). Have we reached the end of poptimism? TheRinger. com, Online at https://www.theringer.com/music/2017/11/16/16666306/taylor-swift-poptimism-2017. Posted November 16, 2017. Accessed June 25, 2021. Hiller RS, Walter JM (2017). The rise of streaming music and implications for music production. Review of Network Economics, 16(4): 351–385. Hofstede G (2001). Culture’s Consequences: Comparing Values, Behaviors, Institutions and Organizations Across Nations. Sage Publications. Hosseini R, Le ND, Zidek JV (2012). Time-varying Markov models for binary temperature series in agrorisk management. Journal of Agricultural, Biological, and Environmental Statistics, 17(2): 283–305. Hyden S (2018). Twilight of the Gods: A Journey to the End of Classic Rock. HarperCollins. Hyndman R, Athanasopoulos G, Bergmeir C, Caceres G, Chhay L, O’Hara-Wild M, et al. (2020). forecast: Forecasting functions for time series and linear models. R package version 8.13. Jain R, Sharma R, Nagrath P, Jain R (2021). Music genre classification chatbot. In: Proceedings of Second International Conference on Computing, Communications, and Cyber-Security, 393–408. Springer. Liang KY, Zeger SL (1986). Longitudinal data analysis using generalized linear models. Biometrika, 73(1): 13–22. Liu M, Hu X, Schedl M (2018). The relation of culture, socio-economics, and friendship to music preferences: A large-scale, cross-country study. PloS One, 13(12): e0208186. Macrotrends (2021a). U.S. GDP growth rate 1961-2021. https://www.macrotrends.net/countries/USA/united-states/gdp-growth-rate. Macrotrends (2021b). U.S. national unemployment rate. https://www.macrotrends.net/1316/us-national-unemployment-rate. March K (2020). Village Voice Pazz & Jop Rip-off Poll’s best albums of 2019. Flood Magazine. Online at https://floodmagazine.com/73002/village-voice-pazz-jop-rip-off-polls-best-albums-of-2019/. Posted January 8, 2020. Accessed February 3, 2022. North AC, Hargreaves DJ (2007). Lifestyle correlates of musical preference: 1. relationships, living arrangements, beliefs, and crime. Psychology of Music, 35(1): 58–87. Pedrero-Esteban LM, Barrios-Rubio A, Medina-Ávila V (2019). Adolescentes, smartphones y consumo de audio digital en la era de spotify. Comunicar, 27: 103–112. Powers D (2013). Writing the Record: The Village Voice and the Birth of Rock Criticism. University of Massachusetts Press. R Core Team (2020). R: A Language and Environment for Statistical Computing. R Foundation for Statistical Computing, Vienna, Austria. Recording Industry Association of America (2021a). U.S. recorded music revenues by format. https://www.riaa.com/u-s-sales-database/. Recording Industry Association of America (2021b). U.S. sales database. https://www.riaa.com/u-s-sales-database/. Rentfrow PJ, Goldberg LR, Levitin DJ (2011). The structure of musical preferences: a five-factor model. Journal of Personality and Social Psychology, 100(6): 1139. Richards C (2015). Do you want poptimism? or do you want the truth? The Washington Post. Online at https://www.washingtonpost.com/entertainment/music/at-the-top-of-the-pop-music-heap-theres-no-criticizing-the-view/2015/04/16/d98d53a8-e1f2-11e4-b510-962fcfabc310_story.html?utm_term=.66c297e6a6f4. Posted April 17, 2015. Accessed June 25, 2021. Robins W (2020). Missing the Pazz & Jop critics poll. PsAudio Copper, 102: 32–35. Online at https://www.psaudio.com/wp-content/plugins/psa-copper-magazine/public/pdf/issue/issue-102.pdf. Accessed June 25, 2021. Sanneh K (2004). The rap against rockism. The New York Times, 31, 351–354. Published October 31, 2004. Schwarz G (1978). Estimating the dimension of a model. Annals of Statistics, 6(2): 461–464. Shapiro SS, Wilk MB (1965). An analysis of variance test for normality (complete samples). Biometrika, 52(3/4): 591–611. Silver D, Lee M, Childress CC (2016). Genre complexes in popular music. PloS One, 11(5): e0155471. Spivack S, Philibotte SJ, Spilka NH, Passman IJ, Wallisch P (2019). Who remembers the Beatles? the collective memory for popular music. PloS One, 14(2): e0210066. Vlegels J, Lievens J (2017). Music classification, genres, and taste patterns: A ground-up network analysis on the clustering of artist preferences. Poetics, 60: 76–89. Warton DI, Hui FK (2011). The arcsine is asinine: the analysis of proportions in ecology. Ecology, 92(1): 3–10. Woolhouse M, Bansal J (2013). Work, rest and (press) play: Music consumption as an indicator of human economic development. Journal of Interdisciplinary Music Studies, 7: 45–71. Yee TW (2021). VGAM: Vector Generalized Linear and Additive Models. R package version 1.1-5.