MOOCad: Visual Analysis of Anomalous Learning Activities in Massive Open Online Courses
Loading...
Date
2019
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
The Eurographics Association
Abstract
The research on Massive Open Online Course (MOOC) has mushroomed worldwide due to the technical revolution and its unprecedented enrollments. Existing work mainly focuses on performance prediction, content recommendation, and learning behavior summarization. However, finding anomalous learning activities in MOOC data has posed special challenges and requires providing a clear definition of anomalous behavior, analyzing the multifaceted learning sequence data, and interpreting anomalies at different scales. In this paper, we present a novel visual analytics system, MOOCad, for exploring anomalous learning patterns and their clustering in MOOC data. The system integrates an anomaly detection algorithm to cluster learning sequences of MOOC learners into staged-based groups. Moreover, it allows interactive anomaly detection between and within groups on the basis of semantic and interpretable group-wise data summaries. We demonstrate the effectiveness of MOOCad via an in-depth interview with a MOOC lecturer with real-world course data.
Description
@inproceedings{10.2312:evs.20191176,
booktitle = {EuroVis 2019 - Short Papers},
editor = {Johansson, Jimmy and Sadlo, Filip and Marai, G. Elisabeta},
title = {{MOOCad: Visual Analysis of Anomalous Learning Activities in Massive Open Online Courses}},
author = {Mu, Xing and Xu, Ke and Chen, Qing and Du, Fan and Wang, Yun and Qu, Huamin},
year = {2019},
publisher = {The Eurographics Association},
ISBN = {978-3-03868-090-1},
DOI = {10.2312/evs.20191176}
}