Abstract
In the context of Industry 5.0, the development of skills through experiential learning is becoming increasingly important in industrial engineering education. However, traditional assessment methods often fail to capture the effectiveness of these activities and the actual skills acquired by students. This gap calls for new, more adaptive and dynamic approaches to evaluation. To address this need, this study proposes an innovative solution that employs recent Generative Artificial Intelligence (GenAI) technology to develop a dynamic and self-adaptive assessment system designed specifically for experiential learning environments. The proposed model uses a web-based, self-correcting quiz integrated with ChatGPT via OpenAI’s API. Questions are dynamically generated according to Bloom's taxonomy, and the student's responses are checked in real time to adapt the subsequent questions accordingly. At the end of each session, the system automatically provides both quantitative scores and qualitative feedback for each response and for the overall performance. An application case was conducted in i-FAB, the learning factory at Università Carlo Cattaneo - LIUC, in which students were involved in an experiential learning activity aimed at learning and practicing the Data Analytics skills considered fundamental in the Industry 5.0 context. The results obtained from the test of the method demonstrated its validity and consistency with the set objectives. The proposed method is thus a significant contribution to experiential learning research, filling the gap of inadequate assessment systems while leaving room for possible future improvements.