cs.CLJun 22, 2026

Language-Specific Sentiment Polarity Biases in Encoder and Large Language Model Classification of Product Reviews

Authors: Advita RajivKavitha KothurGautham Reddy

Organizations: John P. Stevens High School, Edison, NJ 08820 · Ford Foundation, New York, NY 10017 · NC State University, Raleigh, NC 27606

Abstract

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.

Explore similar work

CardsList