Understanding the Perceptions of Healthcare Researchers Regarding ChatGPT: A Study Based on Bidirectional Encoder Representation from Transformers (BERT) Sentiment Analysis and Topic Modeling

• Published in: Annals of biomedical engineering Vol. 51; no. 8; pp. 1654 - 1656
• Main Authors: Praveen, S. V., Vajrobol, Vajratiya
• Format: Journal Article
• Language: English
• Published: Cham Springer International Publishing 01.08.2023; Springer Nature B.V
• Subjects: Biochemistry; Biological and Medical Physics; Biomedical and Life Sciences; Biomedical Engineering and Bioengineering; Biomedicine; Biophysics; Chatbots; Classical Mechanics; Coders; Data mining; Deep learning; Electric Power Supplies; Health care; Humans; Letter to the Editor; Modelling; Representations; Sentiment Analysis; Deep learning; Perception; Natural language processing; Health care research; ChatGPT
• ISSN: 0090-6964; 1573-9686
• DOI: 10.1007/s10439-023-03222-0

In this study, we have used deep learning techniques to understand the perception of researchers in the healthcare sector about the recently introduced chat generative pre-trained transformer (ChatGPT). Ever since the launch of ChatGPT, there have been various debates over the usage of ChatGPT for research purposes. In this article, using the pre-trained BERT (Bidirectional Encoder Representations from Transformers) model, we performed sentiment analysis and topic modeling to analyze the social media posts of healthcare researchers to understand their emotions towards ChatGPT.