Publication Type

Journal Article

Version

publishedVersion

Publication Date

10-2018

Abstract

User grouping in asynchronous online forums is a common phenomenon nowadays. People with similar backgrounds or shared interests like to get together in group discussions. As tens of thousands of archived conversational posts accumulate, challenges emerge for forum administrators and analysts to effectively explore user groups in large-volume threads and gain meaningful insights into the hierarchical discussions. Identifying and comparing groups in discussion threads are nontrivial, since the number of users and posts increases with time and noises may hamper the detection of user groups. Researchers in data mining fields have proposed a large body of algorithms to explore user grouping. However, the mining result is not intuitive to understand and difficult for users to explore the details. To address these issues, we present VisForum, a visual analytic system allowing people to interactively explore user groups in a forum.We work closely with two educators who have released courses in Massive Open Online Courses (MOOC) platforms to compile a list of design goals to guide our design. Then, we design and implement a multi-coordinated interface as well as several novel glyphs, i.e., group glyph, user glyph, and set glyph, with different granularities. Accordingly, we propose the group Detecting & Sorting Algorithm to reduce noises in a collection of posts, and employ the concept of "forum-index" for users to identify high-impact forummembers. Two case studies using real-world datasets demonstrate the usefulness of the system and the effectiveness of novel glyph designs. Furthermore, we conduct an in-lab user study to present the usability of VisForum. © 2018 ACM.

Keywords

MOOC forum, glyph design, application

Discipline

Computer and Systems Architecture | Software Engineering

Research Areas

Software and Cyber-Physical Systems

Publication

ACM Transactions on Interactive Intelligent Systems

Volume

8

Issue

1

First Page

3:1

Last Page

3:21

ISSN

2160-6455

Identifier

10.1145/3162075

Publisher

Association for Computing Machinery (ACM)

Additional URL

https://doi.org/10.1145/3162075

Download

Share

COinS