A Survey on Sentimental Analysis of Student Reviews Using Natural Language Processing (NLP) and Text Mining

Abstract

AbstractSentiment Analysis (SA) is a Natural Language Processing (NLP) application. It's sometimes referred to as “opinion mining” or “emotion extraction”. Sentiment Analysis is a growing area of study in text mining and a popular research subject for opinion mining in education, which analyses and comprehends students’ attitudes toward their learning in order to improve the quality of decision-making. More innovative approaches have been developed in online education, which provide an efficient way to learn irrespective of Gender, geographical discrimination, age, etc. As more and more reviews or feedback are posted during online classes, these messages should be correctly classified to identify the theme behind them. Machine Learning (ML) and Deep Learning (DL) based classification models are used to solve sentiment classification problems. Machine Learning (ML) algorithms Support Vector Machine (SVM), Naïve Bayes (NB), Random Forest (RF) and Decision Tree (DT) and Deep Learning (DL) algorithms especially Convolutional Neural Networks (CNN) and Recurrent Neural Networks (RNN) are most frequently used algorithms for Natural Language processing (NLP). It allows us to have a deeper understanding of the student’s emotions. It may also be used to recognize and analyse feelings in user comments or reviews on various blogs, websites, social media, online communities, and other sites in order to better understand their perspectives. Thus, the most addressed domain was the use of sentiment analysis in the context of higher education and the evaluation of teaching quality. It would be very helpful for instructors to improve learning strategies by assessing both the instructors and students’ progress.KeywordsSentimental analysisOpinion miningEmotion extractionPolarityNatural Language Processing (NLP)Machine learningDeep learningText mining