Given session-based news watch history of users, how can we precisely recommend news articles? Unlike other items for recommendation, the worth of news articles decays quickly and various news sources publish fresh ones every second. Moreover, people frequently select news articles regardless of their personal preferences to understand popular topics at a specific time. Conventional recommendation methods, designed for other recommendation domains, give low performance because of these peculiarities of news articles.
In this paper, we propose PGT (News Recommendation Coalescing Personal and Global Temporal Preferences), an accurate news recommendation method designed with consideration of the above characteristics of news articles. PGT extracts latent features from both personal and global temporal preferences to suciently re ect users' behaviors. Furthermore, we propose an attention based architecture to extract adequate coalesced features from both of the preferences. Experimental results show that PGT provides the most accurate news recommendation, giving the state-of-the-art accuracy.
PGT is described in the following paper:
|Adressa||655,790||8,167,390||43,460||User interations of news articles in Adressa||Adressa Dataset|
|Globo||296,332||2,994,717||46,577||User interations of news articles in Globo||Globo Dataset|