Opinion mining from student text review for choosing better online courses

Abstract

The process of online assessment has utilized get increased gradually as an evaluating tool in order to measure the lectures performance over Institution of Higher Learning (IHLs). However, these approaches generally have questionnaires sets consists of both quantitative and qualitative whereas the teaching assessment systems for several online lecture have concentrated on quantitative questions part due to its quick analysis. Contrarily, the part of qualitative has needed opinion from students that frequently ignored or misplaced and the opinion results level are omitted. This is due to student’s opinion which is generally in term of unstructured text that made hard to analyze the feedback manually. Moreover, the enormous data amount has produced on daily basis which can be utilized to opinion mining for extracting the student’s opinion in this exact online education area that has not widely applied in all educational system. Therefore, this paper has designed a framework by applying opinion mining concept to the student of coursera online machine learning course as the dataset whereas the comparison is accomplished using opinion mining framework to extract. The unstructured text gets processed and classification results based on polarity to obtain better outcome. Hence, this framework maintain several steps namely opinion extraction, unstructured text processing and polarity classification using NLP. Moreover, the performance of the outcome from the Opinion Mining (OM) gets evaluated using machine learning algorithms.