Opinion mining from student feedback data using supervised learning algorithms

This paper explores opinion mining using supervised learning algorithms to find the polarity of the student feedback based on pre-defined features of teaching and learning. The study conducted involves the application of a combination of machine learning and natural language processing techniques on student feedback data gathered from module evaluation survey results of Middle East College, Oman. In addition to providing a step by step explanation of the process of implementation of opinion mining from student comments using the open source data analytics tool Rapid Miner, this paper also presents a comparative performance study of the algorithms like SVM, Naïve Bayes, K Nearest Neighbor and Neural Network classifier. The data set extracted from the survey is subjected to data preprocessing which is then used to train the algorithms for binomial classification. The trained models are also capable of predicting the polarity of the student comments based on extracted features like examination, teaching etc. The results are compared to find the better performance with respect to various evaluation criteria for the different algorithms.