Neural Explainable Recommender Model Based on Attributes and Reviews

作     者：Yu-Yao Liu Bo Yang Hong-Bin Pei Jing Huang Yu-Yao Liu;Bo Yang;Hong-Bin Pei;Jing Huang

作者机构：Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of EducationJilin University Changchun 130012China College of Computer Science and TechnologyJilin UniversityChangchun 130012China 

出 版 物：《Journal of Computer Science & Technology》 (计算机科学技术学报（英文版）)

年 卷 期：2020年第35卷第6期

页      面：1446-1460页

核心收录：

学科分类：0808[工学-电气工程] 08[工学] 081203[工学-计算机应用技术] 0835[工学-软件工程] 0701[理学-数学] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：This work was supported by the University Science and Technology Research Plan Project of Jilin Province of China under Grant No.JJKH20190156KJ the National Natural Science Foundation of China under Grant Nos.61572226 and 61876069 Jilin Province Key Scientific and Technological Research and Development Project under Grant Nos.20180201067GX and 20180201044GX Jilin Province Natural Science Foundation under Grant No.20200201036JC. 

主　　题：recommender system explainable recommendation review usefulness attribute usefulness 

摘      要：Explainable recommendation, which can provide reasonable explanations for recommendations, is increasingly important in many fields. Although traditional embedding-based models can learn many implicit features, resulting in good performance, they cannot provide the reason for their recommendations. Existing explainable recommender methods can be mainly divided into two types. The first type models highlight reviews written by users to provide an explanation. For the second type, attribute information is taken into consideration. These approaches only consider one aspect and do not make the best use of the existing information. In this paper, we propose a novel neural explainable recommender model based on attributes and reviews (NERAR) for recommendation that combines the processing of attribute features and review features. We employ a tree-based model to extract and learn attribute features from auxiliary information, and then we use a time-aware gated recurrent unit (T-GRU) to model user review features and process item review features based on a convolutional neural network (CNN). Extensive experiments on Amazon datasets demonstrate that our model outperforms the state-of-the-art recommendation models in accuracy of recommendations. The presented examples also show that our model can offer more reasonable explanations. Crowd-sourcing based evaluations are conducted to verify our model s superiority in explainability.