Beyond recommendation acceptance: explanation’s learning effects in a math recommender system

Abstract

Recommender systems can provide personalized advice on learning for individual students. Providing explanations of those recommendations are expected to increase the transparency and persuasiveness of the system, thus improve students’ adoption of the recommendation. Little research has explored the explanations’ practical effects on learning performance except for the acceptance of recommended learning activities. The recommendation explanations can improve the learning performance if the explanations are designed to contribute to relevant learning skills. This study conducted a comparative experiment (N = 276) in high school classrooms, aiming to investigate whether the use of an explainable math recommender system improves students’ learning performance. We found that the presence of the explanations had positive effects on students’ learning improvement and perceptions of the systems, but not the number of solved quizzes during the learning task. These results imply the possibility that the recommendation explanations may affect students’ meta-cognitive skills and their perceptions, which further contribute to students’ learning improvement. When separating the students based on their prior math abilities, we found a significant correlation between the number of viewed recommendations and the final learning improvement for the students with lower math abilities. This indicates that the students with lower math abilities may benefit from reading their learning progress indicated in the explanations. For students with higher math abilities, their learning improvement was more related to the behavior to select and solve recommended quizzes, which indicates a necessity of more sophisticated and interactive recommender system.

Learning analytics for student homework activities during a long break: Evidence from K-12 education in Japan

“…The authors claimed that sending a personalized email to students who were predicted to drop out would be effective for retaining students' performance (Pardo et al, 2018). Another conducted in a similar context, a high school Math course in Japan, showed that personalized recommender systems with explanations improved student performance (Dai et al, 2024;. These studies provide us clues for improving the dashboard.…”