TY - GEN
T1 - Ensuring Transparency in Using ChatGPT for Public Sentiment Analysis
AU - Tsai, Chun-Hua
AU - Nandy, Gargi
AU - House, Deanna
AU - Carroll, John M.
N1 - Publisher Copyright:
© 2024 Copyright held by the owner/author(s).
PY - 2024/6/11
Y1 - 2024/6/11
N2 - The advancement of generative AI, involving the utilization of large language models (LLMs) like ChatGPT to assess public opinion and sentiment, has become increasingly prevalent. However, this upsurge in usage raises significant questions about the transparency and interpretability of the predictions made by these LLM Models. Hence, this paper explores the imperative of ensuring transparency in the application of ChatGPT for public sentiment analysis. To tackle these challenges, we propose using a lexicon-based model as a surrogate to approximate both global and local predictions. Through case studies, we demonstrate how transparency mechanisms, bolstered by the lexicon-based model, can be seamlessly integrated into ChatGPT’s deployment for sentiment analysis. Drawing on the results of our study, we further discuss the implications for future research involving the utilization of LLMs in governmental functions, policymaking, and public engagement.
AB - The advancement of generative AI, involving the utilization of large language models (LLMs) like ChatGPT to assess public opinion and sentiment, has become increasingly prevalent. However, this upsurge in usage raises significant questions about the transparency and interpretability of the predictions made by these LLM Models. Hence, this paper explores the imperative of ensuring transparency in the application of ChatGPT for public sentiment analysis. To tackle these challenges, we propose using a lexicon-based model as a surrogate to approximate both global and local predictions. Through case studies, we demonstrate how transparency mechanisms, bolstered by the lexicon-based model, can be seamlessly integrated into ChatGPT’s deployment for sentiment analysis. Drawing on the results of our study, we further discuss the implications for future research involving the utilization of LLMs in governmental functions, policymaking, and public engagement.
UR - http://www.scopus.com/inward/record.url?scp=85195259634&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85195259634&partnerID=8YFLogxK
U2 - 10.1145/3657054.3657128
DO - 10.1145/3657054.3657128
M3 - Conference contribution
AN - SCOPUS:85195259634
T3 - ACM International Conference Proceeding Series
SP - 627
EP - 636
BT - Proceedings of the 25th Annual International Conference on Digital Government Research, DGO 2024
A2 - Liao, Hsin-Chung
A2 - Cid, David Duenas
A2 - Macadar, Marie Anne
A2 - Bernardini, Flavia
PB - Association for Computing Machinery
T2 - 25th Annual International Conference on Digital Government Research, DGO 2024
Y2 - 11 June 2024 through 14 June 2024
ER -