Going Beyond Local: Global Graph-Enhanced Personalized News Recommendations

TL;DR

This paper introduces GLORY, a novel global-local graph neural network model that enhances personalized news recommendations by integrating global user behavior and news representations with local content analysis.

Contribution

The paper presents a new model combining global user behavior graphs with local content-based methods, improving recommendation accuracy and diversity.

Findings

Outperforms existing methods on public datasets

Provides more diverse news recommendations

Effectively integrates global and local information

Abstract

Precisely recommending candidate news articles to users has always been a core challenge for personalized news recommendation systems. Most recent works primarily focus on using advanced natural language processing techniques to extract semantic information from rich textual data, employing content-based methods derived from local historical news. However, this approach lacks a global perspective, failing to account for users' hidden motivations and behaviors beyond semantic information. To address this challenge, we propose a novel model called GLORY (Global-LOcal news Recommendation sYstem), which combines global representations learned from other users with local representations to enhance personalized recommendation systems. We accomplish this by constructing a Global-aware Historical News Encoder, which includes a global news graph and employs gated graph neural networks to enrich news representations, thereby fusing historical news representations by a historical news aggregator. Similarly, we extend this approach to a Global Candidate News Encoder, utilizing a global entity graph and a candidate news aggregator to enhance candidate news representation. Evaluation results on two public news datasets demonstrate that our method outperforms existing approaches. Furthermore, our model offers more diverse recommendations.