DESIGN OF PERSONALIZED EXAM MATERIALS TOOLS ACCORDING TO MULTIPLE INTELLIGENCE TYPE BASED ON SUPERVISED LEARNING

• Main Author: Rachmat, Arif
• Format: Theses
• Language: Indonesia
• Online Access: https://digilib.itb.ac.id/gdl/view/52190
• Institution: Institut Teknologi Bandung

Currently, personalized learning has become a necessity in the learning process. Research and implementation of personalization in the planning phases and implementation phases of learning have been extensively studied. However, that research has not yet reached the application stage in the learning assessment phase. Providing homogeneous examination material to each student has not considered the characteristics of learners. Even though the achievements from the assessment phase will provide a measure of the quality of the learning process as a whole. Personalization in this phase aims to giving opportunities students for expressing themselves and provide a sense of fairness to all learners according to their dominant advantages. This research has analyzed the individual characteristics model, which is derived as a benchmark for identification of the information and characteristics of the test material, which is then formulated into a classification model based on supervised learning. Also conducted an analysis of the needs in the implementation of test personalization. Research in thisi contribution is personalization method to classification test material. Evaluation and testing of the output is measuring the impact of the personalized test simulation results, cross-validation testing on the classification model, and expert justification of the system design. Simulation of assessment has an impact on the reactions of students with the conclusion that interest and learning motivation are very high (86% and 89%). Meanwhile, the impact on knowledge increased by an average value of 3.06%. The number of students on the KKM scale category is quite reduced by 4 students, increasing to the good category (2 students) and very good (2 students). Cross validation test on the multi-label classification model gives accuracy results for the logic type 0.85, the verbal type 0.87, the visual type 0.93, and the natural type 0.96. The expert's justification for the system design gave a very good average response (90%).