Visualizing user activity in open e-learning contexts: challenges and techniques for operational management

This paper describes the practical application of four visualization techniques that have been developed to deal with high-volume, large time-scaled, and high-dimensional data sets that are characteristic of Internet-based user activity. Visualization techniques can be useful for monitoring and studying online user activity in settings where many thousands of users are involved in web-based educational endeavors. Simple numerical summaries of server requests and server performance trends cannot adequately answer the kinds of questions posed by those who desire to understand e-learner activity in web-based e-learning systems. Tracking and understanding remote users and their distant, round-the-clock activities present major technical and analytical challenges, especially in terms of the sheer scale and volume of the generated usage data. With web-based teaching and learning systems, four aspects of the usage tend to hinder analysis: high density, broad time scales, many variables, and veiled patterns. The paper looks at possible solutions in the application of four visualization techniques, using open source statistics software, in the contexts of key scenarios where such techniques can support operations management and decision making processes.

[1]  Vania Dimitrova,et al.  Generation of graphical representations of student tracking data in course management systems , 2005, Ninth International Conference on Information Visualisation (IV'05).

[2]  Teuvo Kohonen,et al.  Self-organization and associative memory: 3rd edition , 1989 .

[3]  William S. Cleveland Internet traffic: visualization, discovery, and very large displays , 2002, IEEE Symposium on Information Visualization, 2002. INFOVIS 2002..

[4]  Helwig Hauser,et al.  Time histograms for large, time-dependent data , 2004, VISSYM'04.

[5]  Dario Bruzzese,et al.  Combining visual techniques for Association Rules exploration , 2004, AVI.

[6]  Sebastián Ventura,et al.  Educational data mining: A survey from 1995 to 2005 , 2007, Expert Syst. Appl..

[7]  Sebastián Ventura,et al.  Mining and Visualizing Visited Trails in Web-Based Educational Systems , 2008, EDM.

[8]  James Stephen Marron,et al.  Mice and Elephants Visualization of Internet Traffic , 2002, COMPSTAT.

[9]  Konstantina Papagiannaki,et al.  Flow classification by histograms: or how to go on safari in the internet , 2004, SIGMETRICS '04/Performance '04.

[10]  Dick Stenmark Identifying clusters of user behavior in intranet search engine log files , 2008, J. Assoc. Inf. Sci. Technol..

[11]  Owen G. McGrath Seeking activity: on the trail of users in open and community source frameworks , 2007, SIGUCCS.

[12]  Noriaki Izumi,et al.  Long Tails and Analysis of Knowledge Worker Intranet Browsing Behavior , 2007, BIS.

[13]  John Alan McDonald,et al.  Interactive graphics for data analysis , 1982 .

[14]  T. Kohonen,et al.  Bibliography of Self-Organizing Map SOM) Papers: 1998-2001 Addendum , 2003 .

[15]  Daniel B. Carr,et al.  Looking at large data sets using binned data plots , 1992 .

[16]  Danyel Fisher,et al.  Distilling Digital Traces: Computational Social Science Approaches to Studying the Internet , 2008 .

[17]  Zdravko Markov,et al.  Data mining the web - uncovering patterns in web content, structure, and usage , 2007 .

[18]  Zdravko Markov,et al.  Comprar Data Mining the Web: Uncovering Patterns in Web Content, Structure, and Usage | Daniel T. Larose | 9780471666554 | Wiley , 2007 .

[19]  Darryl Veitch,et al.  Capturing the Elusive Poissonity in Web Traffic , 2006, 14th IEEE International Symposium on Modeling, Analysis, and Simulation.

[20]  Simon Urbanek,et al.  Interactive graphics for Data Analysis - Principles and Examples , 2008, Computer science and data analysis series.

[21]  Helwig Hauser,et al.  Angular brushing of extended parallel coordinates , 2002, IEEE Symposium on Information Visualization, 2002. INFOVIS 2002..

[22]  Padhraic Smyth,et al.  Visualization of navigation patterns on a Web site using model-based clustering , 2000, KDD '00.

[23]  Niels G. Waller,et al.  A comparison of the classification capabilities of the 1-dimensional kohonen neural network with two pratitioning and three hierarchical cluster analysis algorithms , 1998 .

[24]  Bruce R. Klemz,et al.  Exploratory Analysis using Parallel Coordinate Systems: Data Visualization in N-Dimensions , 2000 .

[25]  A. Yilmaz Çamurcu,et al.  Visual clustering of multidimensional educational data from an intelligent tutoring system , 2010, Comput. Appl. Eng. Educ..

[26]  Eduard Gröller,et al.  Process visualization with levels of detail , 2002, IEEE Symposium on Information Visualization, 2002. INFOVIS 2002..