Answers are grounded in this paper and cite their sources.
In recent years, student remarks have emerged as an essential source of information for comparing teaching pleasant, getting to know effectiveness, and educational services in higher training institutions. Since maximum remarks records are unstructured and hard to analyze manually because the system is time-ingesting and vulnerable to subjectivity. This study applies the Naïve Bayes category algorithm to automatically analyze and classify college students’ remarks into three sentiment classes: Bad, Neutral, and Good. The dataset consisted of 185 student remarks information collected from diverse academic aspects, such as teaching, path content, examinations, laboratory paintings, library centers, and extracurricular activities. The records were processed through cleansing, preprocessing, labeling, encoding, and splitting levels earlier than version training and evaluation. The version overall performance was measured using accuracy, precision, recall, and F1-score metrics. Experimental results confirmed that the version executed an ordinary accuracy of 0.61, with the exceptional overall performance obtained inside the precise magnificence, reaching a precision of 0.67, recall of 0.82, and F1-score of 0.74. The findings display that Naïve Bayes can help automated sentiment evaluation and assist universities in records-driven academic evaluation and choice-making procedures. The proposed technique presents a sensible and green solution for supporting academic institutions display student perceptions, discover provider weaknesses, and constantly improve the pleasantness of academic control strategically.
No takes yet. Share an insight, caveat, or question.
Yasi Dani (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: