Peer reviewed
Download full textERIC Number: ED636600
Record Type: Non-Journal
Publication Date: 2023
Pages: 7
Abstractor: As Provided
ISBN: N/A
ISSN: N/A
EISSN: N/A
Homogeneity of Token Probability Distributions in ChatGPT and Human Texts
Dragica Ljubisavljevic; Marko Koprivica; Aleksandar Kostic; Vladan Devedžic
International Association for Development of the Information Society, Paper presented at the International Association for Development of the Information Society (IADIS) International Conference on Cognition and Exploratory Learning in the Digital Age (CELDA) (20th, Madeira Island, Portugal, Oct 21-23, 2023)
This paper delves into statistical disparities between human-written and ChatGPT-generated texts, utilizing an analysis of Shannon's equitability values, and token frequency. Our findings indicate that Shannon's equitability can potentially be a differentiating factor between texts produced by humans and those generated by ChatGPT. Additionally, we uncover substantial distinctions when studying the most frequent tokens. [For the full proceedings, see ED636095.]
Descriptors: Artificial Intelligence, Man Machine Systems, Natural Language Processing, Writing (Composition), Statistical Analysis, Probability
International Association for the Development of the Information Society. e-mail: secretariat@iadis.org; Web site: http://www.iadisportal.org
Publication Type: Speeches/Meeting Papers; Reports - Research
Education Level: N/A
Audience: N/A
Language: English
Sponsor: N/A
Authoring Institution: N/A
Grant or Contract Numbers: N/A
