Neural Explainable Recommender Model Based on Attributes and Reviews
- PDF / 1,976,738 Bytes
- 15 Pages / 595 x 842 pts (A4) Page_size
- 94 Downloads / 189 Views
Neural Explainable Recommender Model Based on Attributes and Reviews Yu-Yao Liu, Bo Yang, Senior Member, CCF, ACM, IEEE, Hong-Bin Pei and Jing Huang∗ , Member, CCF, ACM, IEEE Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, Jilin University Changchun 130012, China College of Computer Science and Technology, Jilin University, Changchun 130012, China
E-mail: [email protected]; [email protected]; [email protected]; [email protected] Received November 1, 2019; revised May 7, 2020. Abstract 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. Keywords
1
recommender system, explainable recommendation, review usefulness, attribute usefulness
Introduction
Recommender systems are becoming increasingly popular in industry. Recommendation based on representation learning methods that model the recommendation task as score prediction has also achieved success in many fields [1–3] . However, although latent factor based recommendation can extract the implicit features, it cannot provide a reasonable explanation for the recommendation. With the development of recommendation technology, users have higher demand for the credibility of the recommendation. Therefore, it
is important to provide a reasonable recommendation that is both accurate and explainable. 1 Many business websites○ allow users to write reviews about items that contain a lot of additional information, with the user’s profiles and item features related to the current item. These reviews are valuable to other users who are interested in purchasing. Therefore, many existing models use review information as explanations. For example, NARRE (neu
Data Loading...
