Twitter-Based User Modeling for News Recommendations / 2962
Fabian Abel, Qi Gao, Geert-Jan Houben, Ke Tao

In this paper, we study user modeling on Twitter. We investigate different strategies for mining user interest profiles from microblogging activities ranging from strategies that analyze the semantic meaning of Twitter messages to strategies that adapt to temporal patterns that can be observed in the microblogging behavior. We evaluate the quality of the user modeling methods in the context of a personalized news recommendation system. Our results reveals that an understanding of the semantic meaning of microposts is key for generating high-quality user profiles.