Sentiment Analysis on Student Performance Using Novel Ensemble Machine Learning Technique

Sentiment inquiry is used in a variety of sectors and has become one of the most popular subjects in academic exploration, with an expanding body of tasks. Maintaining a positive relationship between students requires academic input. Monitoring a student's progress is critical to their growth and helps instructors, parents, and guardians provide more support. Sentiment analysis is extensively used in a variety of fields, like business, social connections, and education. In an educational setting, this strategy allows students' feedback to be analysed, teachers' teaching performance to be monitored, and the learning experience to be improved. In the educational system, teacher assessment is critical to improving the learning experience in institutions. In this research, the authors propose a novel ensemble machine learning technique for figuring out the best ways to help students study in order to boost their academic achievements. This research assesses the effectiveness of techniques using accuracy, recall, precision, and the f-measure. In order to compare the methods used in this study, the authors used several machine learning approaches, like naive bayes, linear support vector machine, random forests, multilayer perceptron, stochastic gradient decent and logistic regression. When comparing several machine learning algorithms, the suggested ensemble technique produces the best results.

Keywords:

Education , Sentiment Analysis , Machine learning , Ensemble Model