Recommender systems are ubiquitous: from Netflix to Spotify and beyond. But recommendations should not only be personalized; often they need to be contextualized too. However, many context-aware and context-driven recommender systems use a very limited representation of context. We show how we use topic modeling to mine user reviews to obtain a much richer, open ended context representation that we can incorporate into a context-driven recommender system.
Derek Bridge is a Senior Lecturer in the School of Computer Science and Information Technology at University College Cork, Ireland. He has over 30 years’ experience of teaching and research in Artificial Intelligence. He has a PhD in computational linguistics from the University of Cambridge. But he is best known for his research in Case-Based Reasoning and Recommender Systems. In Ireland, he is one of the Principal Investigators in the Insight Centre for Data Analytics, where at national level he leads the Recommender Systems Group, and he is also a Co-Leader of the Science Foundation Ireland Centre for Research Training in AI.