Integrating reviews and ratings into graph neural networks for rating prediction

In the area of recommendation systems, one of the fundamental tasks is rating prediction. Most existing neural network methods independently extract user’s and item’s review features utilizing a parallel convolutional neural network(CNN) and use them as the representation of users and items to predict rating scores. There are two main drawbacks of these methods: (1) They typically only leverage user or item reviews but ignore the latent information provided by user-item interactions. (2) The historical rating scores are not integrated into the representation of users and items, they are simply used as labels to train models. Thus the rating information is not adequately utilized, leading to the prediction performance of these methods is not superior. To remedy these drawbacks mentioned above, in this paper, we build a unified graph convolutional network(GCN) to capture the interaction information between user and item, also obtain additional information provided by reviews and rating scores. As both reviews and ratings carry interactive messages among users and items, they would magnify the learning performance of user-item features. Specifically, we first construct a multi-attributed bipartite graph(MA-bipartite graph) to represent users, items, and their interactions through reviews and ratings. Then we divide the MA-bipartite graph into two sub-graphs according to the attributes of the edge types which represent the user-item interaction in review domain and item domain respectively. Next, an attributed GCN model is explicitly designed to learn latent features of users and items by incorporating review embeddings and rating score weights. Finally, the attention mechanism is carried to fuse user and item features dynamically to conduct the rating prediction. We conduct our experiments on two real-world datasets. The results demonstrate that the proposed model achieved the state-of-the-art performance, which increases the prediction accuracy by more than 3%, compared with baseline methods.