D-HAN: Dynamic News Recommendation with Hierarchical Attention Network

TL;DR

This paper introduces D-HAN, a dynamic news recommendation model that leverages hierarchical attention and continuous time data to better capture user preferences and improve recommendation accuracy.

Contribution

The paper proposes a novel dynamic hierarchical attention network with continuous time integration and dynamic negative sampling for improved news recommendation.

Findings

Effective on three real-world datasets

Outperforms existing static models

Enhances user preference modeling

Abstract

News recommendation models often fall short in capturing users' preferences due to their static approach to user-news interactions. To address this limitation, we present a novel dynamic news recommender model that seamlessly integrates continuous time information to a hierarchical attention network that effectively represents news information at the sentence, element, and sequence levels. Moreover, we introduce a dynamic negative sampling method to optimize users' implicit feedback. To validate our model's effectiveness, we conduct extensive experiments on three real-world datasets. The results demonstrate the effectiveness of our proposed approach.