<![CDATA[Stress can happen to anyone and prolonged stress can cause mental health problems. However, many people continue to be unwilling to consult with mental health professionals about their concerns instead opting to complain on social media, such as Twitter. Many people use Twitter to vent their frustrations, making it possible to utilize text classification to determine someone's stress level from their tweets. In this work, the Support Vector Machine technique with Information Gain feature selection is used for text categorization. The data used in this study were 87 documents with details of 29 'Heavy' class documents, 29 'Medium' class documents, and 29 'Light' class documents. With a k value of 5, the test was run using the K-Fold Cross Validation method, and the distribution of training and test data was 80:20. The comparison of the results between the Support Vector Machine method alone with the combination of the Support Vector Machine and Information Gain methods produces the best accuracy on the Support Vector Machine method alone with an accuracy of 59.11%, precision of 29.99%, recall of 38.67%, and f-measure of 33.53%.]]>
Copyrights © 2022
