Semantics-Enabled User Interest Detection from Twitter

Social networks enable users to freely communicate with each other and share their recent news, ongoing activities or views about different topics. As a result, user interest detection from social networks has been the subject of increasing attention. Some recent works have proposed to enrich social posts by annotating them with unambiguous relevant ontological concepts extracted from external knowledge bases and model user interests as a bag of concepts. However, in the bag of concepts approach, each topic of interest is represented as an individual concept that is already predefined in the knowledge base. Therefore, it is not possible to infer fine-grained topics of interest, which are only expressible through a collection of multiple concepts or emerging topics, which are not yet defined in the knowledge base. To address these issues, we view each topic of interest as a conjunction of several concepts, which are temporally correlated on Twitter. Based on this, we extract active topics within a given time interval and determine a users inclination towards these active topics. We demonstrate the effectiveness of our approach in the context of a personalized news recommendation system. We show through extensive experimentation that our work is able to improve the state of the art.