A Review Paper on the Role of Sentiment Analysis in Quality Education

Education is a critical indication of progress and a major factor in well-being. The UNs Sustainable Development Goals establish specific requirements for increasing educational quality and protecting the well-being of children. UN’s agenda for Sustainable Development Goal 4 which aims to “ensure inclusive and equitable quality education and promote lifelong learning opportunities for all” was adopted in India in 2015. Students’ academic success is a vital part of the education system. Predicting student performance has grown more challenging due to the enormous amount of data in educational databases. Low-performing students will experience a variety of difficulties, including delayed graduation and even dropping out. Therefore, educational institutions should closely monitor the academic progress of their students and provide quick assistance to those who have low performance. Using Students’ academic achievement predictions to accomplish that is one method. This method will help educational institutions in identifying and supporting low-performing students at an initial stage. This study presents a systematic review of research on sentiment analysis towards SDG4 quality education through social media platform such as Twitter, Facebook and a review of 21 studies indexed in SCOPUS. Using social media data rather than a conventional survey of the data, evaluation of outspoken opinion and feelings of students towards their institution to obtain Quality Education. In this study, the dataset is taken from kaggle with names as student-performance-data-set which uses two files named as student-math, and student-por which shows the student performance in a Math language course and Portuguese language course, respectively, with 33 attributes and 396 records in each. Of 396 records, 110 records were selected as sample. During the visualization, we analyzed SVM model is stable because even minor data changes have no impact on the hyperplane and it handles the nonlinear data using Kernel techniques.