<![CDATA[A student is someone who has been attending one of the highest educational institutions for some time. Students have several levels, namely the beginning and the final level. Where the final level is a step to prepare yourself to compile a thesis or final assignment as a condition of graduation becomes one of the toughest obstacles. In several studies conducted in 2019 at one of the universities, 15 students with an average age of 21 partially had mild depression rates of (51.7%), moderate (41.4%), there were 2 high-level depressed students (Mir et al., 2019). As a final-level student depression is a disease that can affect all final students including students instead of the end level. Therefore, depression in students must be treated quickly and appropriately. However, the obstacles to handling require experts or psychologists, plus the lack of people who understand about mental disorders in students. Therefore, a system is needed that can detect early levels of depression in students to be able to stop more serious problems. The study will implement an expert system for early detection of student depression levels using the Support Vector Machine method with a web-based kernel-RBF. . Using 257 data in his tests obtained an average accuracy value of 90.6% and a precision value of 87.8%, recall 83.2%, f1-score 85% and obtained the best SVM parameter value at the value of complexity (C) = 2, gamma (y) = 0.1, and Maxiteration = 1000 with a data ratio of 70%:30%. With good accuracy scores, this study can be implemented to help expert system for early detection of student depression levels using the Support Vector Machine Method.]]>
Copyrights © 2022
