Homophily of music listening in online social networks of China

Homophily, ranging from demographics to sentiments, breeds connections in social networks, either offline or online. However, with the prosperous growth of music streaming services, whether homophily exists in online music listening remains unclear. In this study, two online social networks of the same group of active users who listened to complete songs over 1000 times and posted over 100 tweets are established, separately, in Netease Music and Weibo. Through presented multiple similarity measures, it is evidently demonstrated that homophily does exist in music listening for both online social networks. The unexpected listening similarity in Weibo also implies that knowledge from generic social networks can be confidently transferred to domain-oriented networks for context enrichment and algorithm enhancement. Comprehensive factors that might function in the formation of homophily are further probed, and many interesting patterns are profoundly revealed. It is found that female friends are more homogeneous in music listening and that positive and energetic songs significantly pull users close. Our methodology and findings shed light on realistic applications in online music services.