In this paper, we develop a neural attentive interpretable recommendation system, named NAIRS. A self-attention network, as a key component of the system, is designed to assign attention weights to interacted items of a user. This attention mechanism can distinguish the importance of the various interacted items in contributing to a user profile. Based on the user profiles obtained by the self-attention network, NAIRS offers personalized high-quality recommendation. Moreover, it develops visual cues to interpret recommendations. This demo application with the implementation of NAIRS enables users to interact with a recommendation system, and it persistently collects training data to improve the system. The demonstration and experimental results show the effectiveness of NAIRS.
@article{arxiv.1902.07494,
title = {NAIRS: A Neural Attentive Interpretable Recommendation System},
author = {Shuai Yu and Yongbo Wang and Min Yang and Baocheng Li and Qiang Qu and Jialie Shen},
journal= {arXiv preprint arXiv:1902.07494},
year = {2019}
}
Comments
This paper was published as a demonstration paper on WSDM'19. In this version, we added a detailed related work section