<![CDATA[The COVID-19 pandemic has led to new learning models at universities, posing challenges for educators and students. This situation will likely have an impact on the mental health of most students due to the lack of face-to-face interaction when distance learning is implemented. While social distancing is critical to reducing new cases of COVID-19, implementing new learning models at universities presents significant challenges. This study aims to categorize student interests in discussion room applications by applying machine learning model. The machine learning models employed include Random Forest, Naive Bayes, XGBoost, CatBoost, and LightGBM. The procedure of this research consists of several steps, starting from data collection, data preprocessing, classification, model evaluation, model testing, and deployment. The result shows that Random Forest has performed the best in this classification task compared to other four models. The testing result of the system shows that the recommended academic interest tags are mostly relevant to user preferences, accounting for 71.24%. In addition, this finding offers insights into addressing the pandemics impact on students and highlights technologys potential to improve the educational experience, emphasizing the need for increased mental health resources]]>
Copyrights © 2024
