Klasifikasi Tingkat Stress pada Mahasiswa Teknik Informatika dalam Melakukan Perkuliahan Metode Hybrid Menggunakan Algoritma Naive Bayes

Abstract

The Covid-19 pandemic has forced educational institutions to use hybrid learning methods. This method combines face-to-face and online lectures alternately so that many students become stressed. Stress has many causes. This is what makes researchers interested in conducting research by making predictions of stress levels in students, especially Informatics Engineering students in conducting lectures using the hybrid method. This study will use student profile data which is considered to be a factor causing stress. This study uses the Naive Bayes method. The researcher chose this method because in naive Bayes calculations, the variable data is not only in the form of numbers but can also use words. In addition, the naive Bayes algorithm only requires a small amount of training data to determine the estimated parameters needed in the classification process. This research was conducted by calculating the probability of the training data variable and continued by classifying the testing data. From the evaluation and validation results that have been carried out using the Rapid Miner tools, and from the training data using k-folds cross validation with k = 10, the accuracy results are 73.33%. And after being tested using data testing, the accuracy level results obtained from the classification of stress levels using the Naïve Bayes method obtained results for Accuracy 80.00%, Precision 77.78% and Recall 77.78%.