Is It Enough Just Looking at the Title?: Leveraging Body Text To Enrich Title Words Towards Accurate News Recommendation

Abstract

In a news recommender system, a user tends to click on a news article if she is interested in its topic understood by looking at its title. Such a behavior is possible since, when viewing the title, humans naturally think of the contextual meaning of each title word by leveraging their own background knowledge. Motivated by this, we propose a novel personalized news recommendation framework CAST (Context-aware Attention network with a Selection module for Title word representation), which is capable of enriching title words by leveraging body text that fully provides the whole content of a given article as the context. Through extensive experiments, we demonstrate (1) the effectiveness of core modules in CAST, (2) the superiority of CAST over 9 state-of-the-art news recommendation methods, and (3) the interpretability with CAST.