Sentiment analysis of Faculty of Science and Technology students' satisfaction with the 2024 graduation using the Naïve Bayes method

Abstract

Sentiment analysis of UINSU student graduation based on academic data is one of the efforts to understand the factors that affect the success of student studies. This research aims to analyze the sentiment of UINSU student graduation by utilizing academic data such as cumulative grade point average (GPA), number of credits taken, and other relevant attributes, using the Naive Bayes method. Naive Bayes was chosen because of its ability to classify data efficiently and accurately, even though the data used has noise or inconsistency. The research process begins with collecting student data from the university database, and then data cleaning is carried out to ensure the quality of the data used. Next, the data is processed and classified using the Naive Bayes algorithm in Weka software to predict graduation status based on academic parameters. The results show that the Naive Bayes method is able to produce quite high accuracy in predicting student graduation, with accuracy values ranging from 75% to more than 85% depending on parameter selection and data cleaning. GPA is the most influential attribute on the prediction results, while other attributes such as class activity and organizational experience also contribute, although not as much as GPA. These findings provide important insights for the campus in designing more effective academic coaching and planning programs and can be a reference in the development of data mining-based decision support systems to improve the quality of computer science graduates.