Enhanced Sentiment Detection in Thai University Admissions Using Complement Naive Bayes

This research delves into the pivotal role of social media, particularly Facebook, in influencing public sentiment concerning university admissions. Given that university admissions are a highly discussed topic among students and prospective applicants, this study harnesses advanced natural language processing techniques to scrutinize sentiments expressed through Facebook reactions to related posts. By employing TF-IDF for word weighting and Naive Bayes classification for sentiment categorization, the research aims to construct a model that accurately deciphers emotional responses from users. The results indicate that the model achieves an 80% accuracy rate in predicting reactions, underscoring the potential of sentiment analysis in comprehending public opinion on educational issues. This innovative methodology not only sheds light on the prevailing sentiments surrounding university admissions but also exemplifies the efficacy of social media as a dynamic tool for real-time public sentiment assessment. The implications of this research are profound, offering valuable insights for educational institutions and policymakers in understanding and responding to the sentiments of prospective students.