ScholarWorks@성균관대학교

초록

Although student learning satisfaction has been widely studied, modern techniques such as interpretable machine learning and neural networks have not been sufficiently explored. This study demonstrates that a recent model that combines boosting with interpretability, automatic piecewise linear regression (APLR), offers the best fit for predicting learning satisfaction among several state-of-the-art approaches. Through the analysis of APLR’s numerical and visual interpretations, students’ time management and concentration abilities, perceived helpfulness to classmates, and participation in offline courses have the most significant positive impact on learning satisfaction. Surprisingly, involvement in creative activities did not positively affect learning satisfaction. Moreover, the contributing factors can be interpreted on an individual level, allowing educators to customize instructions according to student profiles. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2026.

키워드