Asymmetrical Hierarchical Networks with Attentive Interactions for Interpretable Review-Based Recommendation
This work addresses the challenge of leveraging user-provided reviews for better recommendations in e-commerce or content platforms, but it is incremental as it builds on existing review-based methods.
The paper tackled the problem of improving review-based recommender systems by addressing the asymmetry between user and item reviews, developing a neural network with asymmetric attentive modules that achieved effective results across multiple real datasets.
Recently, recommender systems have been able to emit substantially improved recommendations by leveraging user-provided reviews. Existing methods typically merge all reviews of a given user or item into a long document, and then process user and item documents in the same manner. In practice, however, these two sets of reviews are notably different: users' reviews reflect a variety of items that they have bought and are hence very heterogeneous in their topics, while an item's reviews pertain only to that single item and are thus topically homogeneous. In this work, we develop a novel neural network model that properly accounts for this important difference by means of asymmetric attentive modules. The user module learns to attend to only those signals that are relevant with respect to the target item, whereas the item module learns to extract the most salient contents with regard to properties of the item. Our multi-hierarchical paradigm accounts for the fact that neither are all reviews equally useful, nor are all sentences within each review equally pertinent. Extensive experimental results on a variety of real datasets demonstrate the effectiveness of our method.