We Are What We Watch: Movie Plots Predict the Personalities of Those who “Like” Them Gideon Nave Marketing Department, The Wharton School, University of Pennsylvania 3730 Walnut St., Philadelphia PA 19104, USA Tel: +1 (215) 898 8248 Email:
[email protected] Jason Rentfrow Social & Developmental Psychology, University of Cambridge Free School Lane, Cambridge, Cambridgeshire, CB2 3RQ, UK Tel: +44 (0)1223 (7) 67805 E-mail:
[email protected] Sudeep Bhatia Psychology Department, University of Pennsylvania 3720 Walnut Street, Philadelphia PA 19104, USA Tel: +1 (215) 898 5096 Email:
[email protected] Acknowledgments We thank Dylan Manfredi for research assistance. We thank Eric Bradlow, Joshua Eliashberg, Nadja C. Furtner, and Olivier Toubia for their comments on earlier versions of the manuscript. Gideon Nave thanks Carlos and Rosa de la Cruz and the Wharton School of Business Dean’s Research Fund for ongoing support. Sudeep Bhatia received funding from the National Science Foundation grant SES-1847794 ABSTRACT The proliferation of media streaming services has increased the volume of personalized video consumption, allowing marketers to reach massive audiences and deliver a range of customized content at scale. However, relatively little is known about how consumers’ psychological makeup is manifested in their media preferences. The present paper addresses this gap in a pre- registered study of the relationship between movie plots, quantified via user-generated keywords, and the aggregate personality profiles of those who “like” them on social media. We find that movie plots can be used to accurately predict aggregate fans’ personalities, above and beyond the demographic characteristics of fans, and general film characteristics such as quality, popularity, and genre.