编码器与大语言模型在产品评论分类中的语言特定情感极性偏差
Language-Specific Sentiment Polarity Biases in Encoder and Large Language Model Classification of Product Reviews
AI总结：
研究AI模型跨语言和架构对正负评论分类准确率的差异，发现大语言模型在法语中有负向偏差，编码器模型在日语中有正向偏差。
摘要：
本研究调查了情感极性偏差，具体而言，AI模型在不同语言和模型架构下对正面与负面评论分类准确率的差异。大语言模型在法语中表现出负向偏差，对负面评论更准确，而编码器模型在日语中表现出正向偏差，忽略了使用间接批评的负面评论。这些语言特定的极性偏差对部署多语言情感分析系统的社会和商业领域都有影响。
英文摘要：
This study investigates sentiment polarity biases, specifically, differences in how accurately AI models classify positive versus negative reviews across languages and model architectures. Large language models show a negative bias in French and are more accurate on negative reviews, while encoder models exhibit positive bias in Japanese, missing negative reviews that use indirect criticism. These language-specific polarity biases have implications in both social and business domains deploying multilingual sentiment analysis systems.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
