Modeling the Dynamics of Learning Activity on the Web

Charalampos Mavroforakis, Isabel Valera, Manuel Gomez-Rodriguez

Abstract: People are increasingly relying on social media and the Web to find solutions to their problems in a wide range of domains. In this setting, closely related problems often lead to the same characteristic learning pattern --- people sharing a similar problem visit closely related pieces of information, perform almost identical queries or, more generally, take a series of similar actions at a similar pace. In this paper, we introduce a novel modeling framework for clustering continuous-time grouped streaming data, the Hierarchical Dirichlet Hawkes process (HDHP), which allows us to automatically uncover a wide variety of learning patterns from detailed traces of learning activity. Our model allows for efficient inference, scaling to millions of actions and thousands of users. Experiments on real data from Stack Overflow reveal that our framework recovers meaningful learning patterns, accurately tracks users' interests and goals over time and achieves better predictive performance than the state of the art.