# Asymmetrical Hierarchical Networks with Attentive Interactions for Interpretable Review-Based Recommendation

arXiv: https://arxiv.org/abs/2001.04346 · HTML: https://mlsanity.com/paper/2001.04346/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Dec 2019.

## Built on by (most cited first, 9 of 9)

- [Shilling Black-box Review-based Recommender Systems through Fake Review Generation](https://mlsanity.com/paper/2306.16526/) (2023)
- [FineRec:Exploring Fine-grained Sequential Recommendation](https://mlsanity.com/paper/2404.12975/) (2024)
- [Dynamic Review-based Recommenders](https://mlsanity.com/paper/2110.14747/) (2021)
- [Review-Based Domain Disentanglement without Duplicate Users or Contexts for Cross-Domain Recommendation](https://mlsanity.com/paper/2110.12648/) (2021)
- [Knowledge-aware Collaborative Filtering with Pre-trained Language Model for Personalized Review-based Rating Prediction](https://mlsanity.com/paper/2308.02555/) (2023)
- [Recommend for a Reason: Unlocking the Power of Unsupervised Aspect-Sentiment Co-Extraction](https://mlsanity.com/paper/2109.03821/) (2021)
- [Review-Based Hyperbolic Cross-Domain Recommendation](https://mlsanity.com/paper/2403.20298/) (2024)
- [An Interpretable Alternative to Neural Representation Learning for Rating Prediction -- Transparent Latent Class Modeling of User Reviews](https://mlsanity.com/paper/2407.00063/) (2024)
- [Bi-NAS: Towards Effective and Personalized Explanation for Recommender Systems via Bi-Level Neural Architecture Search](https://mlsanity.com/paper/2607.01387/) (2026)

## Abstract (arXiv)

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.