ARTIFICIAL INTELLIGENCE IN ACCOUNTING EDUCATION: IDENTIFYING LEARNING STYLES AND ASSESSING INDIVIDUAL DIFFERENCES

Evaluations on the role of artificial intelligence (AI) in education emphasize its potential contributions to student-centered learning and personalized education. However, while studies have begun to explore the expected contributions of these relatively new AI applications, comparative differences—specifically performance assessments—between AI usage and direct human effort are not yet sufficiently developed. Although there are limited studies aimed at determining learning styles through the use of AI, their consistency with actual results is not thoroughly examined. This study aims to assess the individual differences of accounting students at a vocational and technical high education school using the Kolb Learning Style Inventory (KLSI) and to evaluate the performance (consistency) of AI applications (ChatGPT, Gemini, and Copilot) against actual implementations. To this end, responses from 11 vocational and technical high school accounting students, whose learning styles were previously determined using KLSI, were utilized. Three different AI tools were instructed to determine the learning styles of these students using the same commands. In this way, the effectiveness of AI tools in identifying and assessing individual differences among students was examined both independently and comparatively. According to the findings, ChatGPT showed the highest performance, with only one incorrect assessment, while the other AIs made three incorrect assessments. Notably, the observation that ChatGPT incorrectly identified did not overlap with the incorrect observations of the others. In contrast, two of the three incorrect assessments by Gemini and Copilot pertained to the same two observations. Based on all the findings, this study, which provides an initial evaluation of the performance of AI in meeting the expected contributions and, specifically, in using KLSI, suggests that while AI can facilitate the identification and evaluation of individual differences in teaching, the possibility of errors should not be overlooked. Essentially, the study, with its empirical evidence, highlights that AIs still need to continue learning themselves and that relying solely on AI in zero-tolerance-required tasks, such as identifying students' individual characteristics, could be risky.