Modeling Stage-wise Evolution of User Interests for News Recommendation

TL;DR

This paper introduces a unified framework for news recommendation that models both long-term user preferences and short-term interest dynamics by leveraging global and local temporal subgraphs, LSTM, and self-attention mechanisms.

Contribution

It proposes a novel approach combining global and local temporal modeling to better capture evolving user interests in news recommendation systems.

Findings

Outperforms strong baselines on large-scale datasets

Provides more relevant and timely news recommendations

Effectively models both long-term and short-term user interests

Abstract

Personalized news recommendation is highly time-sensitive, as user interests are often driven by emerging events, trending topics, and shifting real-world contexts. These dynamics make it essential to model not only users' long-term preferences, which reflect stable reading habits and high-order collaborative patterns, but also their short-term, context-dependent interests that change rapidly over time. However, most existing approaches rely on a single static interaction graph, which struggles to capture both long-term preference patterns and short-term interest changes as user behavior evolves. To address this challenge, we propose a unified framework that learns user preferences from both global and local temporal perspectives. A global preference modeling component captures long-term collaborative signals from the overall interaction graph, while a local preference modeling component partitions historical interactions into stage-wise temporal subgraphs to represent short-term dynamics. Within this module, an LSTM branch models the progressive evolution of recent interests, and a self-attention branch captures long-range temporal dependencies. Extensive experiments on two large-scale real-world datasets show that our approach consistently outperforms strong baselines and delivers fresher and more relevant recommendations across diverse user behaviors and temporal settings.