Investigating the Effects of Different Levels of User Control in an Interactive Educational Recommender System

2026-05-02

AI Summary

This study systematically investigates how user control at three levels—input (user profiling), process (algorithm), and output (recommendation results)—influences perceived control, transparency, trust, satisfaction, and recommendation quality in educational recommender systems. Building upon the MOOC platform CourseMapper, the authors designed and implemented an interactive recommender system that supports multi-level user control and conducted a between-subjects experiment with 184 participants to empirically evaluate its effects. The findings reveal, for the first time, that input-level control is most critical for enhancing users’ positive perceptions, and that each level of control positively impacts distinct dimensions of user experience in differentiated ways. These results provide both theoretical grounding and practical guidance for designing effective user control mechanisms in educational recommender systems.

Abstract

Educational recommender systems (ERSs) are becoming increasingly important in enhancing educational outcomes and personalizing learning experiences by providing recommendations of personalized resources and activities to learners, tailored to their individual learning needs. While user control is widely assumed to improve user experience, the effects of different levels of control in ERSs remain underexplored. To address this gap, we designed and evaluated an interactive ERS within the MOOC platform CourseMapper, where learners could interact with the input (i.e., user profile), process (i.e., recommendation algorithm), and output (i.e., recommendations) of the system. We conducted a between-subjects user study (N=184) to examine how varying levels of user control in an ERS influenced users' perceptions of the recommendation goals of perceived control, transparency, trust, satisfaction, and perceived quality. Our results show that enabling users to build and refine their profile is sufficient to promote positive perceptions of the ERS, while additional control options mainly reinforce these impressions. Moreover, perceived control is the only goal significantly affected by providing different levels of user control in the ERS, with input control exerting the strongest influence. Furthermore, different levels of control affect transparency, trust, satisfaction, and perceived quality in distinct yet interconnected ways. Overall, the findings provide empirical evidence that user control positively shapes transparency, trust, satisfaction, and perceived quality, though to varying extents.

Problem

• user control
• educational recommender systems
• perceived control
• transparency
• trust

Innovation

• user control
• educational recommender system
• transparency
• trust
• personalization