Katalog Plus
Bibliothek der Frankfurt UAS
Bald neuer Katalog: sichern Sie sich schon vorab Ihre persönlichen Merklisten im Nutzerkonto: Anleitung.
Dieses Ergebnis aus ERIC kann Gästen nicht angezeigt werden.  Login für vollen Zugriff.

Exploring ChatGPT's Ability to Classify the Structure of Literature Reviews in Engineering Research Articles

Title: Exploring ChatGPT's Ability to Classify the Structure of Literature Reviews in Engineering Research Articles
Language: English
Authors: Maha Issa (ORCID 0009-0005-3319-4811); Marwa Faraj (ORCID 0009-0001-0158-9895); Niveen AbiGhannam (ORCID 0000-0002-8823-3479)
Source: IEEE Transactions on Learning Technologies. 2024 17:1859-1868.
Availability: Institute of Electrical and Electronics Engineers, Inc. 445 Hoes Lane, Piscataway, NJ 08854. Tel: 732-981-0060; Web site: http://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=4620076
Peer Reviewed: Y
Page Count: 10
Publication Date: 2024
Document Type: Journal Articles; Reports - Research
Descriptors: Artificial Intelligence; Intelligent Tutoring Systems; Research Reports; Literature Reviews; Content Analysis; Engineering; Editing; Quality Control; Technical Writing
DOI: 10.1109/TLT.2024.3409514
ISSN: 1939-1382
Abstract: ChatGPT is a newly emerging artificial intelligence (AI) tool that can generate and assess written text. In this study, we aim to examine the extent to which it can correctly identify the structure of literature review sections in engineering research articles. For this purpose, we conducted a manual content analysis by classifying paragraphs of literature review sections into their corresponding categories that are based on Kwan's model, which is a labeling scheme for structuring literature reviews. We then asked ChatGPT to perform the same categorization and compared both outcomes. Numerical results do not imply a satisfactory performance of ChatGPT; therefore, writers cannot fully depend on it to edit their literature reviews. However, the AI chatbot displays an understanding of the given prompt and is able to respond beyond the classification task by giving supportive and useful explanations for the users. Such findings can be especially helpful for beginners who usually struggle to write comprehensive literature review sections since they highlight how users can benefit from this AI chatbot to revise their drafts at the level of content and organization. With further investigations and advancement, AI chatbots can also be used for teaching proper literature review writing and editing.
Abstractor: As Provided
Entry Date: 2024
Accession Number: EJ1429542
Database: ERIC