# How Useful are Reviews for Recommendation? A Critical Review and Potential Improvements

arXiv: https://arxiv.org/abs/2005.12210 · HTML: https://mlsanity.com/paper/2005.12210/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 May 2020.

## Built on by (most cited first, 24 of 24)

- [Data Distillation: A Survey](https://mlsanity.com/paper/2301.04272/) (2023)
- [LLM-Rec: Personalized Recommendation via Prompting Large Language Models](https://mlsanity.com/paper/2307.15780/) (2023)
- [Infinite Recommendation Networks: A Data-Centric Approach](https://mlsanity.com/paper/2206.02626/) (2022)
- [Towards Personalized Answer Generation in E-Commerce via Multi-Perspective Preference Modeling](https://mlsanity.com/paper/2112.13556/) (2021)
- [A Survey on Fairness-aware Recommender Systems](https://mlsanity.com/paper/2306.00403/) (2023)
- [Time to Split: Exploring Data Splitting Strategies for Offline Evaluation of Sequential Recommenders](https://mlsanity.com/paper/2507.16289/) (2025)
- [On Sampling Collaborative Filtering Datasets](https://mlsanity.com/paper/2201.04768/) (2022)
- [Fast Multi-Step Critiquing for VAE-based Recommender Systems](https://mlsanity.com/paper/2105.00774/) (2021)
- [Self-Supervised Bot Play for Conversational Recommendation with Justifications](https://mlsanity.com/paper/2112.05197/) (2021)
- [Beyond Static Testbeds: An Interaction-Centric Agent Simulation Platform for Dynamic Recommender Systems](https://mlsanity.com/paper/2505.16429/) (2025)
- [Augmenting the User-Item Graph with Textual Similarity Models](https://mlsanity.com/paper/2109.09358/) (2021)
- [Effects of Multi-Aspect Online Reviews with Unobserved Confounders: Estimation and Implication](https://mlsanity.com/paper/2110.01746/) (2021)
- [Retrieval-Augmented Review Generation for Poisoning Recommender Systems](https://mlsanity.com/paper/2508.15252/) (2025)
- [Review-Based Domain Disentanglement without Duplicate Users or Contexts for Cross-Domain Recommendation](https://mlsanity.com/paper/2110.12648/) (2021)
- [Counterfactual Inference for Eliminating Sentiment Bias in Recommender Systems](https://mlsanity.com/paper/2505.03655/) (2025)
- [Recommendation Is a Dish Better Served Warm](https://mlsanity.com/paper/2508.07856/) (2025)
- [On Faithfulness and Coherence of Language Explanations for Recommendation Systems](https://mlsanity.com/paper/2209.05409/) (2022)
- [Adversarial Text Rewriting for Text-aware Recommender Systems](https://mlsanity.com/paper/2408.00312/) (2024)
- [RECipe: Does a Multi-Modal Recipe Knowledge Graph Fit a Multi-Purpose Recommendation System?](https://mlsanity.com/paper/2308.04579/) (2023)
- [Enriching User Shopping History: Empowering E-commerce with a Hierarchical Recommendation System](https://mlsanity.com/paper/2403.12096/) (2024)
- [Review-Based Hyperbolic Cross-Domain Recommendation](https://mlsanity.com/paper/2403.20298/) (2024)
- [How Much Do Reviews Really Contribute? A Study on Text-Enriched Matrix Factorization for Recommendations](https://mlsanity.com/paper/2606.16973/) (2026)
- [LLM-Derived Priors for Thompson Sampling in Cold-Start Comment Recommendation](https://mlsanity.com/paper/2608.03382/) (2026)
- [Residual Dominance as a Structural Account of Last-Item Reliance in Causal Self-Attention Recommenders](https://mlsanity.com/paper/2608.14021/) (2026)

## Abstract (arXiv)

We investigate a growing body of work that seeks to improve recommender systems through the use of review text. Generally, these papers argue that since reviews 'explain' users' opinions, they ought to be useful to infer the underlying dimensions that predict ratings or purchases. Schemes to incorporate reviews range from simple regularizers to neural network approaches. Our initial findings reveal several discrepancies in reported results, partly due to (e.g.) copying results across papers despite changes in experimental settings or data pre-processing. First, we attempt a comprehensive analysis to resolve these ambiguities. Further investigation calls for discussion on a much larger problem about the "importance" of user reviews for recommendation. Through a wide range of experiments, we observe several cases where state-of-the-art methods fail to outperform existing baselines, especially as we deviate from a few narrowly-defined settings where reviews are useful. We conclude by providing hypotheses for our observations, that seek to characterize under what conditions reviews are likely to be helpful. Through this work, we aim to evaluate the direction in which the field is progressing and encourage robust empirical evaluation.