Multifaceted Sentiment Detection System (MSDS) to Avoid Dropout in Virtual Learning Environment using Multi-class Classifiers

Sentiment analysis with machine learning plays a vital role in Higher Educational Institutions (HEI) for decision making. Technology-enabled interactions can only be successful when strong student-teacher link is established, and the emotions of students are clearly comprehended. The paper aims at proposing Multifaceted Detection System (MSDS) detecting sentiments higher education participating virtual to classify comments posted by them using Machine Learning (ML) algorithms. Present research evaluated total n=1590 students’ presence three specific multifaceted characteristics each providing 530 perform Analysis (SA) monitoring their sentiments, opinions that facilitate predicting dropout environment (VLE). This begins phrase extraction; then data pre-processing techniques namely digits, punctuation marks stop-words removal, spelling correction, tokenization, lemmatization, n-grams, POS (Part Speech) applied. Texts vectorized two feature extraction count vectorization TF-IDF metrics classified four multiclass supervised ML Random Forest, Linear SVC, Multinomial Naive Bayes, Logistic Regression sentiment classification. Analyzing feedback classifies positive, negative, or even more refined enables prediction. Experimental results reveal highest mean accuracy result device efficiency, cognitive behavior, technological expertise cloud platform usage were achieved 98.49%, SVC 93.58% 92.08% respectively. Practically, confirm feasibility behavioral patterns risk VLE.