ERIC Number: EJ1480139
Record Type: Journal
Publication Date: 2025-Aug
Pages: 36
Abstractor: As Provided
ISBN: N/A
ISSN: ISSN-1360-2357
EISSN: EISSN-1573-7608
Available Date: 2025-03-12
Exploring ChatGPT as a Virtual Tutor: A Multi-Dimensional Analysis of Large Language Models in Academic Support
Education and Information Technologies, v30 n12 p17447-17482 2025
This study explores the impact of ChatGPT, an advanced Large Language Model (LLM), as a virtual tutor in online education across five key dimensions: answering questions, writing assistance, study resources, exam preparation, and availability. Utilizing an experimental design, 68 undergraduate students from a public university interacted with ChatGPT over a 15-week academic semester. Data were collected through a validated questionnaire and analyzed using descriptive statistics, correlation analysis, and multiple regression. Findings reveal that students generally perceive ChatGPT as a valuable tool, with a high mean rating across dimensions such as exam preparation (M = 3.38, SD = 1.26) and availability (M = 3.55, SD = 1.34). The correlation analyses showed significant interdependencies between dimensions, with the highest correlation coefficient observed between writing assistance and exam preparation (Kendall's tau-b = 0.45, p < 0.01). Multiple regression analysis identified writing assistance ([beta] = 0.35, p < 0.01) and exam preparation ([beta] = 0.40, p < 0.01) as significant predictors of overall effectiveness. These findings suggest that ChatGPT's multiple functionalities do not operate independently but instead complement and reinforce each other, resulting in a more supportive and integrated learning environment. The study's findings highlight the transformative potential of LLMs to address the limitations of traditional Intelligent Tutoring Systems (ITSs) and offer a more comprehensive and personalized approach to online learning support. The study, however, identifies key areas for enhancing the LLM-based learning environment including the need for greater contextual engagement in learning materials and more comprehensive and personalized feedback mechanisms. The implications of these findings and future research directions are further discussed.
Descriptors: Artificial Intelligence, Natural Language Processing, Man Machine Systems, Intelligent Tutoring Systems, Electronic Learning, Undergraduate Students, Instructional Effectiveness
Springer. Available from: Springer Nature. One New York Plaza, Suite 4600, New York, NY 10004. Tel: 800-777-4643; Tel: 212-460-1500; Fax: 212-460-1700; e-mail: customerservice@springernature.com; Web site: https://link-springer-com.bibliotheek.ehb.be/
Publication Type: Journal Articles; Reports - Research
Education Level: Higher Education; Postsecondary Education
Audience: N/A
Language: English
Sponsor: N/A
Authoring Institution: N/A
Grant or Contract Numbers: N/A
Author Affiliations: 1University of Technology and Applied Sciences, Preparatory Studies Centre, Nizwa, Oman

Peer reviewed
Direct link
