Answers are grounded in this paper and cite their sources.
This research delves into sentiment analysis within the educational sector, recognizing the growing importance of emotions in human experiences. This study attempts to interpret the emotional undercurrents running through student replies by leveraging the capabilities of Natural Language Processing (NLP) and machine learning techniques. The main emphasis of this study is the prediction of student attitudes, and the Multinomial Naive Bayes (MNB) classifier stood out as a standout performer, obtaining a stunning accuracy rate of 79.29%. This finding demonstrates the power of NLP approaches in extracting subtle emotional states from textual data. This study goes beyond the model’s performance to include data pretreatment, text featurization, and a comparative evaluation of multiple models on alternative feature representations. Furthermore, the studyillustrates students’ emotions, creating a realistic picture of the emotional environment inside the academic arena. Understanding student attitudes has become a vital tool for educational institutions looking to improve the student experience as the educational landscape continues to shift. This study establishes the groundwork for decoding students’ emotional mosaics, providing insights that may be used to influence academic tactics and treatments, eventually leading to a more comprehensive and sympathetic educational ecology.
No takes yet. Share an insight, caveat, or question.
Mukhopadhyay et al. (2023) studied this question.