A Framework for Accurate Recommendation and Explanation Generation Using Multi-task Learning
Abstract
Recommendation systems predict desirable items for users based on their past interactions such as ratings, likes, and shopping history. However, these systems face challenges, including data insufficiency and lack of transparency. Leveraging user reviews has been proposed as a solution to address these challenges. User reviews serve as valuable supplementary data sources by conveying user preferences. Additionally, they provide a rich language source that can be used to generate textual explanations, thereby overcoming transparency issues. Therefore, this paper aims to utilize user reviews to enhance the accuracy of recommender systems and generate explanations for recommended items. These explanations help users understand various aspects of the recommended item from the perspective of real users. The use of textual explanations is prevalent in a wide range of explainable recommendation systems. However, previous works often overlook the writing style of users, which can significantly impact the effectiveness of explanations. Thus, the main objective of this paper is to develop a novel framework that incorporates user writing styles and preferences into the explanation generation process for recommendations. Results show that the developed multitask learning framework improves the accuracy of the recommendations. Furthermore, the generated explanations effectively support the induced recommendations.