Analysis of Student Sentiments towards the Use of Artificial Intelligence in Education Using the Naïve Bayes Algorithm

Abstract

The rapid development of Artificial Intelligence (AI) has significantly transformed the field of education. Generative AI applications such as ChatGPT, Gemini, and Microsoft Copilot are increasingly utilized by students to obtain information, assist in completing academic tasks, and improve learning effectiveness. This study aims to analyze students' sentiment toward the use of AI in education using the Naïve Bayes algorithm. Data were collected through questionnaires distributed to high school students in Palu City, Central Sulawesi Province, and processed through text preprocessing stages, including case folding, tokenization, stopword removal, and stemming. The dataset was divided into training and testing data to evaluate the model using a confusion matrix, accuracy, precision, recall, and F1-score. The findings indicate that the Naïve Bayes algorithm performs well in classifying students' sentiments toward AI in education. Most students expressed neutral sentiments regarding the use of AI in learning, while others reported positive and negative perceptions related to its benefits and potential risks. This study provides empirical insights into students' perceptions of AI in education and may serve as a reference for technology-based learning strategies. Students are encouraged to use AI wisely while maintaining critical thinking, analytical skills, and independent learning.