Beyond Language Barriers: Evaluating the Efficacy of Open-Source LLMs in Analyzing Sentiment in Non-English Textual Data

• In Event: Large Language Models for Social Science

Brief Overview

Cross-language sentiment analysis is challenging for non-English texts. This study uses open-source LLMs to analyze Japanese media sentiment on AI, comparing results with mainstream methods to validate open-source LLMs for multilingual analysis

Authors

• Laurence-Olivier M. Foisy, Universite Laval

• Camille Pelletier, Universite Laval

• Hubert Cadieux, Universite Laval

• Étienne Proulx, Universite Laval

• Sarah-Jane Vincent, Universite Laval

• Yannick Dufresne, Universite Laval