FACILITATING LEARNING ANALYTICS OF LEARNER COMMUNICATION IN MOOCS: A VISUAL ANALYTICS APPROACH
Open Access
- Author:
- Wong, Jian Syuan
- Graduate Program:
- Information Sciences and Technology
- Degree:
- Doctor of Philosophy
- Document Type:
- Dissertation
- Date of Defense:
- November 20, 2020
- Committee Members:
- Xiaolong Zhang, Dissertation Advisor/Co-Advisor
Xiaolong Zhang, Committee Chair/Co-Chair
John Yen, Committee Member
Fred Fonseca, Committee Member
Anthony C Robinson, Outside Member
Mary Beth Rosson, Program Head/Chair - Keywords:
- MOOCs
MOOC forum
Visual Analytics
Learning Analytics
Visualization - Abstract:
- Many massive open online courses (MOOCs) offer mainly video-based lectures, which limit the opportunity for interactions and communications among students and instructors. Thus, MOOCs provider often provides online discussion forum tools to facilitate learner interaction and communication. Having massive forum messages posted by learners every day, MOOC forums are regarded as an important information source for understanding learners’ activities and opinions. However, the high volume and heterogeneity of MOOC forum contents make it challenging to analyze forum data effectively from different perspectives of discussions and to integrate diverse information into a coherent understanding of issues of concern. To address these challenges, this study proposes a visual analytic approach to enhance MOOC forum analysis in this dissertation. Visual analytics can leverage the advantages of automated data analysis techniques, interactive visualization, and human cognition to facilitate the analysis. The proposed work aims at helping MOOC instructors to gain a better understanding of forum discussions from different data aspects, including general discussion topic, sentiments expressed in forum messages, and interactions between forum learners. In this research, a prototyping visual analytics application, MessageLens, was first developed. MessageLens is an experimental creation in which tasks and design consideration are primarily derived from the related research. With various visual representations and interactive features, it enables the investigations to be conducted with different data perspectives and at varying levels of granularity. Later, to make the visual analytics design more beneficial, an enhanced application, ForumLens, was introduced. The design and development of ForumLens was based on the information needs of interviews with MOOC instructors. In the improved work, supplemental information such as temporal information is incorporated to uncover the trends of discussion topics and forum user interactions. Our research suggests an approach to analyzing not only MOOC discussion forums but also the other types of online communications that comprise rich communication contents as well as dynamic social interactions among people.