<![CDATA[Overall health depends on mental health or psychological well-being. Mental and physical well being are equally vital. One in two young people under the age of 25 will experience mental health issues at some point, and 75% of mental illnesses begin before the age of 25. Female university students are among those at the highest risk for mental health issues. Typically, students in their early and final semesters experience a high level of academic anxiety. One of the main factors causing psychological distress in students is the final project or thesis. This study aims to classify mental health levels, namely stress and anxiety, by training a classification model that makes use of the Support Vector Machine algorithm. The dataset used in this study is derived from a questionnaire distributed to final-year female students working on their thesis. The dataset consists of 249 records and is divided into two datasets for stress and anxiety classification. The results of this study show the highest accuracy in the stress classification dataset using the RBF and polynomial kernels, reaching 68% with the RBF kernel at gamma 1 and C 100. Meanwhile, the highest accuracy in the anxiety classification dataset reached 50% achieved with the polynomial kernel at degree 3 and C 100. The application of the best model indicates that the most influential features in the Stress and Anxiety datasets are Literature Review, Support System, and Analysis Method. The obtained accuracy can be used as a standard for upcoming studies using more complex data.]]>
Copyrights © 2024
