A Capsule Network for Recommendation and Explaining What You Like and Dislike

TL;DR

This paper introduces CARP, a capsule network model that improves recommendation accuracy by extracting and reasoning about user preferences and item features from reviews, while also providing interpretable explanations.

Contribution

The paper proposes a novel capsule network architecture with a Routing by Bi-Agreement mechanism to extract and reason about logic units from reviews for better rating prediction and explanation.

Findings

CARP outperforms state-of-the-art models in prediction accuracy.

The model effectively discovers interpretable reasons behind user preferences.

Extensive experiments validate the model's robustness across diverse datasets.

Abstract

User reviews contain rich semantics towards the preference of users to features of items. Recently, many deep learning based solutions have been proposed by exploiting reviews for recommendation. The attention mechanism is mainly adopted in these works to identify words or aspects that are important for rating prediction. However, it is still hard to understand whether a user likes or dislikes an aspect of an item according to what viewpoint the user holds and to what extent, without examining the review details. Here, we consider a pair of a viewpoint held by a user and an aspect of an item as a logic unit. Reasoning a rating behavior by discovering the informative logic units from the reviews and resolving their corresponding sentiments could enable a better rating prediction with explanation. To this end, in this paper, we propose a capsule network based model for rating prediction with user reviews, named CARP. For each user-item pair, CARP is devised to extract the informative logic units from the reviews and infer their corresponding sentiments. The model firstly extracts the viewpoints and aspects from the user and item review documents respectively. Then we derive the representation of each logic unit based on its constituent viewpoint and aspect. A sentiment capsule architecture with a novel Routing by Bi-Agreement mechanism is proposed to identify the informative logic unit and the sentiment based representations in user-item level for rating prediction. Extensive experiments are conducted over seven real-world datasets with diverse characteristics. Our results demonstrate that the proposed CARP obtains substantial performance gain over recently proposed state-of-the-art models in terms of prediction accuracy. Further analysis shows that our model can successfully discover the interpretable reasons at a finer level of granularity.