Knowledge-Guided Article Embedding Refinement for Session-Based News Recommendation

Personalized news recommendation aims to recommend news articles to customers, by exploiting the personal preferences and short-term reading interest of users. A practical challenge in personalized news recommendations is the lack of logged user interactions. Recently, the session-based news recommendation has attracted increasing attention, which tries to recommend the next news article given previous articles in an active session. Current session-based news recommendation methods mainly extract latent embeddings from news articles and user-item interactions. However, many existing methods could not exploit the semantic-level structural information among news articles. And the feature learning process simply relies on the news articles in training data, which may not be sufficient to learn semantically rich embeddings. This brief presents a context-aware graph embedding (CAGE) approach for session-based news recommendation. It employs external knowledge graphs to improve the semantic-level representations of news articles. Moreover, graph neural networks are incorporated to further enhance the article embeddings. In addition, we consider the similarity among sessions and design attention neural networks to model the short-term user preferences. Extensive results on multiple news recommendation benchmark datasets show that CAGE performs better than some competitive baselines in most cases.