E-Learning
Amplify E-Learning Intelligence with Visual Analytics
Amplify E-Learning Intelligence with Visual Analytics
In the era of big data, the rich data accumulated by the online learning industry have brought new inspirations to instruction intelligence and tutorial services. Processing vast amounts of information into knowledge and improving data utilization capabilities have become opportunities for these new inspirations. Visualization has a direct and close connection with knowledge expression and is an important means of interpreting complex data.
We are E-Learning group of HKUST VisLab. In order to help educators have a deeper understanding of students' online learning behavior and performance, we have explored this study for years and published many related work in this field. We also build some useful open-source techniques on user behavior data collection, online course data visualization and etc. If you have interests in our works, please feel free to contact us.
Educational areas data, such as online tutorial videos and students' interaction records, are all our playgrounds to provide instruction intelligence via visual analytics.
Advanced data mining and deep learning models guarantee us to tackle with billions of course videos and interaction logs extracted from different E-Learning platforms.
Except the basic visualization representation, we introduce and amplify visual anlytics to facilitate instruction intelligence.
Would you like to know more or just discuss something?
We developed novel visualization techniques to help domain experts to analyze large-scale data of MOOCs. It provides course instructors and education analysts with intuitive, interactive and detailed analysis of the MOOC data including clickstream data when students interact with course videos, grading data for assignments and exams, and forum data. More specifically, our data visualization techniques help users explore the MOOC data from the following perspectives: video popularity, click stream analysis, demographic distribution, user forum interactions, dropout analysis and sequence analysis. Multi-exploration techniques are offered for analysis at different levels. With the help of our data visualization techniques, course instructors/designers and learning analysts can conduct detailed exploration of the learners’ learning behaviors in an intuitive way, gain deep insights into the students’ learning behaviors and further improve their course designs with evidence-based guidance.
We developed a general interaction data collection technique, which could collect students' fine-grained mouse movement data during the problem-solving process, and deployed the techinique on a K-12 resource-based E-Learning platform since the early 2019 to collect data for research. Based on the collected data, we analyzed the detailed problem-solving sequences and built several novel and intuitive visualization systems, such as QLens and SeqDynamics, which aim at help the platform to infer students' cognitive state in the dynamic problem-solving process. What's more, we extracted the interaction features from students' mouse movement trajectories to predict their performances on any given questions and recommend personalized learning paths.
We have conducted extensive research on online learning and below is a list of our recent papers that are supported by this E-learning project.
Peer-inspired Student Performance Prediction in Interactive Online Question Pools with Graph Neural Network
CIKM, 2020
Author: Haotian Li, Huan Wei, Yong Wang, Yangqiu Song, Huamin Qu
Links: [pdf]
Using Information Visualization to Promote Students’ Reflection on “Gaming the system” in Online Learning
L@S, 2020
Author: Meng Xia, Yuya Asano, Joseph Jay Williams, Huamin Qu, Xiaojuan Ma
Links: [pdf]
SeqDynamics: Visual Analytics for Evaluating Online Problem-solving Dynamics
EuroVis, 2020
Author: Meng Xia, Min Xu, Chuan-en Lin, Ta Ying Cheng, Huamin Qu, Xiaojuan Ma
Links: [pdf]
Predicting Student Performance in Interactive Online QuestionPools Using Mouse Interactions
ACM LAK (Learning Analytics & Knowledge), 2020
Author: Huan Wei, Haotian Li, Meng Xia, Yong Wang, Huamin Qu
Links: [pdf]
Visual Analytics of Student Learning Behaviors on K-12 Mathematics E-learning Platforms
IEEE VIS Posters, 2019 (Best Poster Award)
Author: Meng Xia, Huan Wei, Min Xu, Leo Yu Ho Lo, Yong Wang, Rong Zhang, Huamin Qu
Links: [pdf]
MOOCad: Visual Analysis of Anomalous Learning Activities in Massive Open Online Courses
EuroVis 2019 Short Paper
Author: Xing Mu, Ke Xu, Qing Chen, Fan Du, Yun Wang, Huamin Qu
Links: [pdf]
PeerLens: Peer-inspired Interactive Learning PathPlanning in Online Question Pool
ACM CHI, 2019
Author: Meng Xia, Mingfei Sun, Huan Wei, Qing Chen, Yong Wang, Lei Shi, Huamin Qu, Xiaojuan Ma
Links: [pdf]
StageMap: Extracting and Summarizing Progression Stages in Temporal Event Sequences
IEEE Conference on Big Data, 2018
Author: Yuanzhe Chen, Abishek Puri, Linping Yuan, Huamin Qu
Links: [pdf]
ViSeq: Visual Analytics of Learning Sequence in Massive Open Online Courses
IEEE Transactions on Visualization & Computer Graphics, 2018
Author: Qing Chen, Xuanwu Yue, Xavier Plantaz, Yuanzhe Chen, Conglei Shi, Ting-Chuen Pong, Huamin Qu
Links: [pdf]
VisForum: A visual analysis system for exploring user groups in online forums
ACM Transactions on Interactive Intelligent Systems (ACM TiiS), 2018
Author: Siwei Fu, Yong Wang, Yi Yang, Qingqing Bi, Fangzhou Guo, Huamin Qu
Links: [pdf]
A Narrative Visualization Approach For Massive Open Online Courses Data Analysis
HKUST Mphil Thesis, 2018
Author: Zhen Li (Supervisor: Huamin Qu)
Visual Analytics and Storytelling of Data from Massive Open Online Courses
HKUST PhD Thesis, 2018
Author: Qing Chen (Supervisor: Huamin Qu)
Visual Analytics of Online Communication
HKUST PhD Thesis, 2018
Author: Siwei Fu (Supervisor: Huamin Qu)
Visual Analytics of Temporal Event Data
HKUST PhD Thesis, 2018
Author: Yuanzhe Chen (Supervisor: Huamin Qu)
Visual Analysis of MOOC Forums with iForum
IEEE Transactions on Visualization & Computer Graphics, 2017
Author: Siwei Fu, Jian Zhao, Weiwei Cui, Huamin Qu
Links: [pdf]
DropoutSeer: Visualizing Learning Patterns in Massive Open Online Courses for Dropout Reasoning and Prediction
IEEE Conference on Visual Analytics Science and Technology (VAST), 2016
Author: Yuanzhe Chen, Qing Chen, Mingqian Zhao, Sebastien Boyer, Kalyan Veeramachaneni, Huamin Qu
Links: [pdf]
NetworkSeer: Visual Analysis for Social Network in MOOCs
Pacific Visualization Symposium (PacificVis), 2016
Author: Tongshuang Wu, Yuan Yao, Yuqing Duan, Xinzhi Fan, Huamin Qu
Links: [pdf]
PeakVizor: Visual Analytics of Peaks in Video Clickstreams from Massive Open Online Courses
IEEE Transactions on Visualization & Computer Graphics, 2016
Author: Qing Chen, Yuanzhe Chen, Dongyu Liu, Conglei Shi, Yingcai Wu, Huamin Qu
Links: [pdf]
A Narrative Visualization System for Peaks in Video Clickstreams from Massive Open Online Courses
HKUST TLE Mphil Thesis, 2016
Author: Chengjin Li (Supervisor: Huamin Qu)
VisMOOC: Visualizing Video Clickstream Data from Massive Open Online Courses
IEEE Pacific Visualization Symposium (PacificVis), 2015
Author: Conglei Shi, Siwei Fu, Qing Chen, Huamin Qu
Links: [pdf]
Visual Analytics of Data from MOOCs
IEEE Computer Graphics and Applications (CG&A) 2015
Author: Huamin Qu, Qing Chen
Links: [pdf]
VisMooc
A visualization technique to analyze and visualize user's active behaviors for MOOCs by utilizing large-scale data.
MouseTrack
A general data collection technique to collect user's all kinds of mouse interaction data from a webpage.
SeqDynamics
A visualization technique to evaluates user’s problem-solving dynamics from both cognitive and non-cognitive perspectives.
huamin@cse.ust.hk, iris.xia@connect.ust.hk
RM4203, Hong Kong University of Science and Technology, Clear Water Bay, Sai Kung, New Territories, Hong Kong
