Saved in:
Bibliographic Details
Main Authors: Pan, Le, Cao, Yuanjiang, Huang, Chengkai, Zhang, Wenjie, Yao, Lina
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2505.03655
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915275536859136
author Pan, Le
Cao, Yuanjiang
Huang, Chengkai
Zhang, Wenjie
Yao, Lina
author_facet Pan, Le
Cao, Yuanjiang
Huang, Chengkai
Zhang, Wenjie
Yao, Lina
contents Recommender Systems (RSs) aim to provide personalized recommendations for users. A newly discovered bias, known as sentiment bias, uncovers a common phenomenon within Review-based RSs (RRSs): the recommendation accuracy of users or items with negative reviews deteriorates compared with users or items with positive reviews. Critical users and niche items are disadvantaged by such unfair recommendations. We study this problem from the perspective of counterfactual inference with two stages. At the model training stage, we build a causal graph and model how sentiment influences the final rating score. During the inference stage, we decouple the direct and indirect effects to mitigate the impact of sentiment bias and remove the indirect effect using counterfactual inference. We have conducted extensive experiments, and the results validate that our model can achieve comparable performance on rating prediction for better recommendations and effective mitigation of sentiment bias. To the best of our knowledge, this is the first work to employ counterfactual inference on sentiment bias mitigation in RSs.
format Preprint
id arxiv_https___arxiv_org_abs_2505_03655
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Counterfactual Inference for Eliminating Sentiment Bias in Recommender Systems
Pan, Le
Cao, Yuanjiang
Huang, Chengkai
Zhang, Wenjie
Yao, Lina
Information Retrieval
Artificial Intelligence
Recommender Systems (RSs) aim to provide personalized recommendations for users. A newly discovered bias, known as sentiment bias, uncovers a common phenomenon within Review-based RSs (RRSs): the recommendation accuracy of users or items with negative reviews deteriorates compared with users or items with positive reviews. Critical users and niche items are disadvantaged by such unfair recommendations. We study this problem from the perspective of counterfactual inference with two stages. At the model training stage, we build a causal graph and model how sentiment influences the final rating score. During the inference stage, we decouple the direct and indirect effects to mitigate the impact of sentiment bias and remove the indirect effect using counterfactual inference. We have conducted extensive experiments, and the results validate that our model can achieve comparable performance on rating prediction for better recommendations and effective mitigation of sentiment bias. To the best of our knowledge, this is the first work to employ counterfactual inference on sentiment bias mitigation in RSs.
title Counterfactual Inference for Eliminating Sentiment Bias in Recommender Systems
topic Information Retrieval
Artificial Intelligence
url https://arxiv.org/abs/2505.03655