Exploration and Explanation: An Interactive Course Recommendation System for University Environments Boxuan Ma a , Min Lu b , Yuta Taniguchi a and Shin’ichi Konomi b a Kyushu University, Graduate School of Information Science and Electrical Engineering, Fukuoka, Japan b Kyushu University, Faculty of Arts and Science, Fukuoka, Japan Abstract The abundance of courses available in university and the highly personalized curriculum is ofen overwhelming for students who must select courses relevant to their academic interests. A large body of research in course recommendation systems focuses on optimizing prediction and improving accuracy. However, those systems usually aford little or no user interaction, and little is known about the infuence of user-perceived aspects for course recommendations, such as transparency, con- trollability, and user satisfaction. In this paper, we argue that involving students in the course recommendation process is important, and we present an interactive course recommendation system that provides explanations and allows students to explore courses in a personalized way. A within-subject user study was conducted to evaluate our system and the results show a signifcant improvement in many user-centric metrics. Keywords Course Recommendation, Visualization, Exploration, Explanation 1. Introduction A course recommendation system suggests a student de- cide what they should study as per their requirements, which can solve the increasingly severe problem of infor- mation overload of course selection. Diferent from the traditional movie recommendation domain or music rec- ommendation domain, the interaction factor is essential for course recommendations in universities. Course recommendations in universities particularly sufer from the cold start problem. Every year, there are freshmen enroll in, who have difculty navigating their new academic and environment. It is difcult for a tradi- tional course recommendation system to make successful suggestions for those new students without enough avail- able information. Moreover, the necessary information is ofen too small to generate precise recommendations even for senior students. One common practice is using popular courses regardless of students’ interests when the system is short of students’ information and behav- ior. However, a promising alternative is to capture their preferences interactively. That is, if we could involve students in the recommendation process, we may get better results. Many researchers have focused on recommending courses Proceedings of the ACM IUI 2021 Workshops, April 13–17, 2021, College, USA E ma.boxuan.611@s.kyushu-u.ac.jp (B. Ma); lu@artsci.kyushu-u.ac.jp (M. Lu); yuta.taniguchi.y.t@gmail.com (Y. Taniguchi); konomi@artsci.kyushu-u.ac.jp (S. Konomi) O 0000-0002-1566-880X (B. Ma); 0000-0001-7503-1301 (M. Lu); 0000-0003-3298-8124 (Y. Taniguchi); 0000-0001-5831-2152 (S. Konomi) © 2021 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0). CEUR Workshop Proceedings CEUR Workshop Proceedings (CEUR-WS.org) that align with students’ interests extracted from their his- torical data, but students may not choose courses based purely on their interests. For instance, many students have no idea what they want to study, and their choice of courses is aimless [1]. Besides, student interests and goals can change as they explore and learn new things, their preferences extracted from historical data may dif- fer from their current interests. So, involving the student in the recommendation process becomes more signifcant than in other domains. Also, the cost to students of making an inappropriate decision is much higher than investing two hours watch- ing a movie they don’t like or listening to a song they are not interested. In a domain such as a course recommen- dation and learning goal discovery in universities, course selection is a low-frequency behavior. Students only need to make decisions every new semester for four academic years. However, it can have a long-lasting efect on the student as improperly selecting courses would seriously afect their course achievements, even leads students to drop out. Recently, a large body of research focuses on devel- oping course recommendation systems. However, those systems aford little user interaction and lack options to control how recommendations are produced. To address these challenges which have not been well explored in the research community, this work presents an interac- tive course recommendation system by combining visu- alization techniques with recommendation techniques to support the diverse information needs of students. The interactive feature stresses user involvement with the system, allows users to fexibly explore large-item spaces while providing a high level of user control and trans- parency [2]. Also, our proposed approach could increase