News Recommendations by Combining Intra-session with Inter-session and Content-Based Probabilistic Modelling.

Recommender systems in news industry use the time dimension to reveal users’ preferences over time, but they miss to exploit adequately the information encapsulated inside user sessions. Here, we combine intra- with inter-session item transition probabilities to reveal the short- and long-term intentions of individuals along with the public preference over news topic categories. Thus, we are able to better capture the similarities among items that are co-selected inside a session but also within any two consecutive sessions. We have evaluated experimentally our method and compare it against state-of-the-art algorithms on two real-life datasets. We show the superiority of our method over its competitors.