| dc.description.abstract | Universities offer students the flexibility to personalize their academic paths while ensuring compliance with graduation requirements. However, students often face challenges in course selection due to the numerous criteria that must be objectively evaluated to identify the most suitable options for their needs and goals. Prior work has investigated solutions using either interactive visualization or recommender systems. Interactive visualization alone has limitations, such as the manual effort required from users to input, filter, and analyze the data effectively. Recommender systems, on the other hand, face issues such as the filter bubble, which can steer students toward similar or popular choices and restrict academic exploration, as well as the cold start problem, where new users have no prior data, making accurate recommendations difficult. The Dewantara Course Recommender System (Dewantara CRS) presented in this thesis offers a hybrid solution that integrates a recommender system with interactive visualization to support students in making informed course selection decisions. By combining these approaches, the cold start problem and filter bubble are expected to be mitigated through the integration of an AHP Treemap with a knowledge-based recommender system. The significant manual effort required by knowledge-based recommender systems is addressed through features provided by interactive visualization. Students can configure their personal preferences using a drag feature, which are then presented in a compact AHP Treemap visualization. The total value of all categories in the treemap, both default and adjusted, is displayed in a bar chart showing the ranking of courses along with relevant course information and each student’s preferences. Based on the evaluation conducted, the proposed approach demonstrates the potential to enhance decision-making efficiency and personalization in academic course selection. | |
