用反事实推理消除推荐系统中的情感偏见，让差评用户和小众商品更公平。
Counterfactual Inference for Eliminating Sentiment Bias in Recommender Systems
- 构建因果图，分离情感对评分的直接与间接影响。
- 反事实推断有效降低负面评价带来的推荐偏差，性能不下降。
- 首次将反事实推理用于推荐系统的感情偏见缓解，适合做公平推荐的研究者。
推荐系统（RSs）旨在为用户提供个性化推荐。新发现的‘情感偏见’揭示了基于评论的推荐系统（RRSs）中一种普遍现象：相比正面评价的用户或物品，带有负面评价的用户或物品的推荐准确率显著下降。这导致关键用户和小众物品受到不公平对待。本文从反事实推理角度出发，分两阶段研究该问题：在模型训练阶段，构建因果图并建模情感如何影响最终评分；在推理阶段，通过反事实推理解耦直接与间接效应，移除情感的间接影响。大量实验验证，该方法在评分预测上表现良好，同时有效缓解情感偏见。据我们所知，这是首个将反事实推理应用于推荐系统情感偏见缓解的工作。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。