Modeling Multi-interest News Sequence for News Recommendation

TL;DR

This paper introduces the MINS model, which effectively captures multiple user interests from news sequences using self-attention and parallel interest networks, leading to improved news recommendation accuracy.

Contribution

The paper presents a novel multi-interest news sequence model that explicitly models multiple user interests for more accurate session-based news recommendation.

Findings

MINS outperforms state-of-the-art models on real-world datasets.

The self-attention based news encoder effectively captures news representations.

Parallel interest network accurately extracts multiple user interests.

Abstract

A session-based news recommender system recommends the next news to a user by modeling the potential interests embedded in a sequence of news read/clicked by her/him in a session. Generally, a user's interests are diverse, namely there are multiple interests corresponding to different types of news, e.g., news of distinct topics, within a session. %Modeling such multiple interests is critical for precise news recommendation. However, most of existing methods typically overlook such important characteristic and thus fail to distinguish and model the potential multiple interests of a user, impeding accurate recommendation of the next piece of news. Therefore, this paper proposes multi-interest news sequence (MINS) model for news recommendation. In MINS, a news encoder based on self-attention is devised on learn an informative embedding for each piece of news, and then a novel parallel interest network is devised to extract the potential multiple interests embedded in the news sequence in preparation for the subsequent next-news recommendations. The experimental results on a real-world dataset demonstrate that our model can achieve better performance than the state-of-the-art compared models.