Prediction of Sentiment Analysis on Educational Data based on Deep Learning Approach

Abstract

Recognizing and categorizing user’s sentiments from a part of text into different sentiments is known as sentiment analysis. For instance, emotions such as happy, sad, angry or positive, negative or neutral to determine the users attitude concerning a certain subject or object. Sentiment analysis is one of the utmost active research areas in natural language processing, web mining and text mining. It plays an important role in many fields like management sciences and social sciences including education, where student feedback is essential to assess the effectiveness of learning technologies. With increase in educational organizations, online learning portals have fascinated by many students by offering free courses with no fee. Heaps of learners enroll in these massive online courses every year and further review their sentiments about the course content and quality of education. Also, provide suggestions in blogs in order to improve the quality of teaching by giving positive or negative sentiments. This paper proposes a model based on Deep Learning approach to perform sentiment analysis on Educational data. In this paper we focused on the accuracy and performance of the training data set to predict the best model. MLP and SVM are recognized as the outperforming models.