Perception of Bias in ChatGPT: Analysis of Social Media Data

Outlet Title

IEEE Global Conference on Artificial Intelligence and Internet of Things

Authors

Abdullah Wahbeh, Slippery Rock University of PennsylvaniaFollow
Mohammad Al-Ramahi, Texas A&M UniversityFollow
Omar F. El-Gayar, Dakota State UniversityFollow
Ahmed El Noshokaty, California State University - San BernardinoFollow
Tareq Nasralah, Northeastern UniversityFollow

Document Type

Article

Publication Date

2023

Abstract

In this study, we aim to analyze the public perception of Twitter users with respect to the use of ChatGPT and the potential bias in its responses. Sentiment and emotion analysis were also analyzed. Analysis of 5,962 English tweets showed that Twitter users expressed concerns regarding six predominant types of biases, namely: political, ideological, data and algorithmic, gender, racial, cultural, and confirmation biases. Sentiment analysis showed that most of the users reflected a neutral sentiment, followed by negative and positive sentiment. Emotion analysis mainly reflected anger, disgust, and sadness with respect to bias concerns with ChatGPT use.

Recommended Citation

Wahbeh, Abdullah; Al-Ramahi, Mohammad; El-Gayar, Omar F.; El Noshokaty, Ahmed; and Nasralah, Tareq, "Perception of Bias in ChatGPT: Analysis of Social Media Data" (2023). Research & Publications. 414.
https://scholar.dsu.edu/bispapers/414