D-HAN: Dynamic News Recommendation with Hierarchical Attention Network
This addresses the problem of capturing users' evolving preferences in news recommendation, but appears incremental as it builds on existing hierarchical attention and negative sampling techniques.
The paper tackles the problem of static user-news interactions in news recommendation by proposing a dynamic model that integrates continuous time information with a hierarchical attention network and dynamic negative sampling. The results show effectiveness on three real-world datasets, though no concrete numbers are provided.
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.