Prompt2Rec: Prompt based user and item re-characterizing method for recommendation

Collaborative Filtering (CF), which utilizes user-item interaction data is widely adopted in Recommendation System; however, CF encounters challenges such as the cold-start problem and data sparsity. To address this issue, research incorporating Natural Language Processing (NLP) has made progress in leveraging review texts that contain rich information about user preferences and item attributes. Nevertheless, the conventional approach of integrating the entire review text and using it as an input, which has been widely used in previous research, can be vulnerable to noise (i.e., data with little relevance to user preferences or item attributes). In this study, we propose a novel user and item re-characterizing method called Prompt2Rec, which introduces the Prompt-based learning paradigm of NLP. It generates key factors that newly defined essential user and item characteristics from review texts and uses them as new information to train the recommendation model. We validate our proposed method through experiments on five benchmark datasets. The results show that Prompt2Rec leads to improved performance compared to existing methods that rely on review texts. Furthermore, we explore the potential to provide explanations for recommendations by visualizing the model's attention weights on the key factors.