Understanding the focal points and sentiment of learners in MOOC reviews: A machine learning and SC‐LIWC‐based approach

Abstract

Despite the popularity of massive open online courses (MOOCs), only a small portion of the course participants successfully complete the course. The low completion rate can be partially attributed to the mismatch between the participants' expectations and value delivered by the courses. Therefore, this study leverages MOOC reviews to investigate the focal point and sentiment of the learners by combining machine learning techniques and statistical analysis. Several text mining methods (ie, simplified Chinese‐linguistic inquiry and word count dictionary, word embeddings, and bidirectional long short‐term memory model) are combined to automatically extract the emotional and cognitive aspects, review focal point, and sentiment from the learner discourse. Multiple linear regression (MLR) analysis is performed to examine the relationships between the learner sentiment and the extracted content features. Using a set of real data from NetEase online open courses, our results reveal that the MOOC reviews mostly pertain to teaching and platform rather than the course content. Furthermore, the social process and personal concerns appear more frequently in the learner discourse. Overall, the learners exhibit positive attitudes towards teaching and platform and negative attitudes towards issues related to the course content. This study contributes to the literature regarding the MOOC research methodologies and provides a deeper understanding of the learner discourse behaviour in MOOCs.

A Systematic Review of Questionnaire-Based Quantitative Research on MOOCs

“…Data mining and deep learning emphasize correlation judgments between samples and infer the population from the standard data set (Peral et al, 2017). What is more, researchers can apply data mining and deep learning to analyze objective behaviors and subjective perceptions of MOOC learners and instructors, make feature profiles of users, and propose personalized optimization schemes (Geng et al, 2020;Cagiltay et al, 2020…”

Marriage and Family Therapists’ Reporting of Telehealth Use on Practice Websites during COVID-19: A Linguistic Analysis

“…The software program Linguistic Inquire Word Count (LIWC; Francis & Booth, 1993;Pennebaker et al, 2001), was used for the textual analysis. The LIWC has been translated in multiple languages (Meier et al, 2019;Zhao et al, 2016), used in different fields of study (Geng et al, 2020;Kidd & Castano, 2013;Pennebaker et al, 2014), and found to be a valid instrument (Bantum & Owen, 2009;Kahn et al, 2007).). The authors input the website descriptions of COVID-19 and telehealth into the program to derive statistical information about the text.…”

Reviewer Experience vs. Expertise: Which Matters More for Good Course Reviews in Online Learning?

“…With the proliferation of online customer reviews, they now serve as an important and indispensable information source for a wide range of products and services. Online platforms, such as those for e-commerce [36], hotels [37], restaurants [38], touristic destinations [39], movies [40], and online education [6], commonly maintain an online review system for users to share their opinions. Online customer reviews play crucial roles in alleviating information asymmetry, reducing uncertainty, and shaping the informed decision making regarding a purchase of customers [41].…”

“…This difficulty is further amplified by the varying quality of and complexity in quality assessment on online courses, as well as the limited information and expertise of prospective learners in selecting courses [5]. To provide prospective learners with useful information and enable the sharing of course experience among learners, MOOC platforms commonly maintain a course review system that allows learners to post course reviews [6][7][8]. Learner reviews usually consist of a numeric rating and a short free-style textual comment to express learner opinions on courses.…”