View Item 
        •   Utrecht University Student Theses Repository Home
        • UU Theses Repository
        • Theses
        • View Item
        •   Utrecht University Student Theses Repository Home
        • UU Theses Repository
        • Theses
        • View Item
        JavaScript is disabled for your browser. Some features of this site may not work without it.

        Browse

        All of UU Student Theses RepositoryBy Issue DateAuthorsTitlesSubjectsThis CollectionBy Issue DateAuthorsTitlesSubjects

        Dewantara CRS: Interactive Visualization to Support Decision Making for Course Selection

        Thumbnail
        View/Open
        UU_Thesis_Zaki__final_rev.pdf (5.513Mb)
        Publication date
        2025
        Author
        Zakiyamani, Muhamad
        Metadata
        Show full item record
        Summary
        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.
        URI
        https://studenttheses.uu.nl/handle/20.500.12932/50029
        Collections
        • Theses
        Utrecht university logo