Improving Latent User Models in Online Social Media
This work is significant for social media platforms and online learning environments, as it improves the accuracy of user characterization and future behavior prediction, especially for users with sparse data.
The paper addresses the challenge of user-level sparsity in social media by proposing a mutual-enhancement framework that simultaneously partitions users and learns latent activity profiles. This framework achieved significant gains, averaging 15%, over state-of-the-art behavior models, with even greater improvements for users with limited interaction data.
Modern social platforms are characterized by the presence of rich user-behavior data associated with the publication, sharing and consumption of textual content. Users interact with content and with each other in a complex and dynamic social environment while simultaneously evolving over time. In order to effectively characterize users and predict their future behavior in such a setting, it is necessary to overcome several challenges. Content heterogeneity and temporal inconsistency of behavior data result in severe sparsity at the user level. In this paper, we propose a novel mutual-enhancement framework to simultaneously partition and learn latent activity profiles of users. We propose a flexible user partitioning approach to effectively discover rare behaviors and tackle user-level sparsity. We extensively evaluate the proposed framework on massive datasets from real-world platforms including Q&A networks and interactive online courses (MOOCs). Our results indicate significant gains over state-of-the-art behavior models ( 15% avg ) in a varied range of tasks and our gains are further magnified for users with limited interaction data. The proposed algorithms are amenable to parallelization, scale linearly in the size of datasets, and provide flexibility to model diverse facets of user behavior.