STUDY: Socially Aware Temporally Causal Decoder Recommender Systems
This work addresses the challenge of tailoring book recommendations for dyslexic students, an incremental improvement in domain-specific recommender systems.
The paper tackles the problem of improving recommender systems for demographic groups with distinct interests by incorporating social network information, introducing STUDY, a socially-aware architecture that is more efficient to train and achieves more accurate predictions of student engagement for dyslexic or struggling readers compared to existing methods.
Recommender systems are widely used to help people find items that are tailored to their interests. These interests are often influenced by social networks, making it important to use social network information effectively in recommender systems. This is especially true for demographic groups with interests that differ from the majority. This paper introduces STUDY, a Socially-aware Temporally caUsal Decoder recommender sYstem. STUDY introduces a new socially-aware recommender system architecture that is significantly more efficient to learn and train than existing methods. STUDY performs joint inference over socially connected groups in a single forward pass of a modified transformer decoder network. We demonstrate the benefits of STUDY in the recommendation of books for students who are dyslexic, or struggling readers. Dyslexic students often have difficulty engaging with reading material, making it critical to recommend books that are tailored to their interests. We worked with our non-profit partner Learning Ally to evaluate STUDY on a dataset of struggling readers. STUDY was able to generate recommendations that more accurately predicted student engagement, when compared with existing methods.