<![CDATA[In the context of higher education, the final assignment represents the last step in a student's academic journey, a period where students are particularly susceptible to stress. Implementing machine learning techniques, such as the Support Vector Machine (SVM) method, presents a promising approach for early classification of students' stress levels and offers tailored stress management recommendations. This study adopts a quantitative research approach, aimed at classifying student stress levels using the SVM algorithm known for its high prediction accuracy. The research methodology encompasses stages like data collection, preprocessing, classification, results analysis, and accuracy evaluation. In this research, 80% of the dataset is allocated for training, while the remaining 20% is reserved for testing. The study finds that the most effective SVM kernel function is the Radial Basis Function (RBF) with a γ parameter value of 1, which, when applied using RapidMiner, achieves an accuracy of 93.33%. This research is anticipated to make a significant contribution to the development of early stress detection systems for students and offer valuable insights into leveraging machine learning technology for mental health applications. The findings demonstrate that the SVM method with the RBF kernel provides highly accurate classification results, making it a useful tool for effectively identifying student stress level]]>
Copyrights © 2024
