Abstract

Due to the growing quantity of information available on the Web, recommender systems have become crucial component for the success of online shopping stores. However, most of the existing recommender systems were only designed to improve the recommendation results and ignore the explainable recommendation aspect. Therefore, in this paper we propose a long short-term memory deep learning framework for explainable recommendation, that is able to generate an efficient explanation for any rating made by users for a recommended item. Such a framework would help users to choose a product with confident after reading the automatically generated explanation by our framework. The generated explanation is a concise sentence that shows the reason behind a recommendation, i.e., why a user should select that product. Extensive experiments on a real-world dataset from Amazon are conducted with the goal to evaluate the effectiveness of the proposed method in terms of loss and accuracy metrics. The experimental results demonstrate the effectiveness of our method according to the diversity in generating explainable recommendation.

Information

Item Type:	Conference
Divisions:	» Laboratory of Computer Science and Mathematics » Faculty of Science and Technology
ePrint ID:	2190
Date Deposited:	2020-06-05
Further Information:	Google Scholar
URI:	https://www.univ-soukahras.dz/en/publication/article/2190

BibTex