Joint Reason Generation and Rating Prediction for Explainable Recommendation

Jihua Zhu, Yujiao He, Guoshuai Zhao, Xuxiao Bu, Xueming Qian

Abstract: Most recommendation systems focus on predicting rating or finding aspect information in reviews to understand user preferences and item properties. However, these methods ignore the effectiveness and persuasiveness of recommendation results. Consequently, explainable recommendation, namely providing recommendation results with recommendation reasons at the same time, has attracted increasing attention of researchers due to its ability in fostering transparency and trust. It is lucky that some E-commerce websites provide a kind of new interaction box called Tips and users can express their comments on items with a simple sentence. This brings us an opportunity to realize explainable recommendation. Under the supervision of two explicit feedbacks, namely rating and textual tips, we can implement a multi-task learning model which can provide recommendation results and generate recommendation reasons at the same time. In this paper, we propose an <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">E</b> ncoder-Decoder and <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">M</b> ulti-Layer Perception (MLP) based <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">E</b> xplainable <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">R</b> ecommendation model named <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">EMER</i> to simultaneously implement reason generation and rating prediction. Item’s title contains significant product-related information and plays an important role in grabbing user’s attention, so we fuse it in our model to generate recommendation reasons. Numerous experiments on benchmark datasets demonstrate that our model is superior to the state-of-the-art models.