Building Rich User Profiles for Personalized News Recommendation

Nowadays, more and more people are using online news platforms as their main source of information about daily life events. Users of such platforms have access to an increasing amount of articles of different topics, stories, and view points. Thus, a news personalization service is needed to filter the flow of available information and satisfy users needs. To this end, it is crucial to understand and build accurate profiles for both users and news articles. In this paper, we propose a new approach that exploits users comments to recommend articles. We build the profile of each user based on (1) the set of entities he talked about it in his comments, (2) and the set of aspects related to those entities. The same information is extracted from the content of each news article to create its profile. These profiles are then matched for the purpose of recommendation. We have used a collection based on real users activities in four news web sites, namely The Independent, The Telegraph, CNN and ALJazeera. The first results show that our approach outperforms baseline approaches achieving high accuracy.