<![CDATA[The outbreak of the COVID-19 pandemic is increasingly affecting the high level of stress in humans. Stress due to this pandemic has also occurred, especially for students. This stress is caused by students spending too much time studying online. Using student data can act as a tool to identify student stress by processing it through various machine-learning methods. This method can extract information and find patterns and information from the data. Classification techniques are used as data groupings based on mapping data into sample data. This study used several classification methods: Naïve Bayes, Decision Tree, Support Vector Machine (SVM), Neural Network, Random Tree, Random Forest, and K Nearest Neighbor (KNN). These methods were successfully compared to determine which is the best for detecting stress precisely and accurately based on the classification performance results of each method. Random Tree and Decision tree were chosen as the best methods for the results of this performance comparison with an 80:20 split reaching up to 100%.]]>
Copyrights © 2023
