Text Analytics on Course Reviews from Coursera Platform

Abstract

Ratings and reviews are always the major consideration factor by online course seekers before they join the course. However, it can be time-consuming to read all the information especially the course reviews. In this research work, our objective is to propose a text analytics pipeline that includes text cleaning, text lemmatization, sentiment analysis, text mining, and visualization that can help course seekers to gain a quick insight into the courses as well as enables them to make a quick comparison between multiple courses. The proposed text analytic pipeline was created in Python Jupyter Notebook. Three different Python-related courses were chosen for the study. The proposed text analytics pipeline solution was proved able to achieve our research objective. It can help course seekers to gain a quick insight including the positive and negative reviews into the courses as well as enables them to make a quick comparison between multiple courses. The n-gram analysis and word cloud generated were sufficient to provide an accurate and informative glance into the course. However, it fell short on sentiment analysis especially in detecting the negative reviews.