Sentimental Analysis on Student Feedback using NLP & POS Tagging

Abstract

Sentiment analysis has been extensively used in a variety of fields in the previous decade, including business, social media, and education. The usage of sentiment analysis is rising, but it remains difficult, particularly in the education area, where the nature of the language utilized by pupils and a sizeable amount of information, dealing with their processing thoughts is a difficult task. Several studies of the literature illustrate the current state of sentiment analysis application which include sector from various perspectives and circumstances. In the teaching analysis system, the qualifier sentimental words for student feedback aren’t thought of the result of teaching analysis through student feedback isn’t displayed whether positive or negative opinion. To efficiently utilize sentimental analysis for the teaching system through student feedback, this paper proposes to analyze the scholar’s text feedback automatically using NLP and post-tagging based approach to conclude the extent of teaching work. Here, the main concentration is applying sentimental analysis for students’ feedback, collected through online mode. The use of ML and the NLP approach to examine the feelings of the students included in the text document is used for classification based on students’ comments to predict the polarity (positive/ negative). A total of 2200 student feedback are collected and analyzed, which results in 60 percentage positive and 40 percentage negative through Post Tagging.