Monitoring student progress using virtual appliances: A case study

  • Authors:
  • Vicente-Arturo Romero-Zaldivar;Abelardo Pardo;Daniel Burgos;Carlos Delgado Kloos

  • Affiliations:
  • AtoS Research & Innovation, Albarracíín, 25 28037, Madrid, Spain;Department of Telematics Engineering, University Carlos III of Madrid, Av. Universidad, 30, 28911 Leganés (Madrid), Spain;International University of La Rioja, Gran Vía Rey Juan Carlos I 41, 26002 Logroño, Spain;Department of Telematics Engineering, University Carlos III of Madrid, Av. Universidad, 30, 28911 Leganés (Madrid), Spain

  • Venue:
  • Computers & Education
  • Year:
  • 2012

Quantified Score

Hi-index 0.00

Visualization

Abstract

The interactions that students have with each other, with the instructors, and with educational resources are valuable indicators of the effectiveness of a learning experience. The increasing use of information and communication technology allows these interactions to be recorded so that analytic or mining techniques are used to gain a deeper understanding of the learning process and propose improvements. But with the increasing variety of tools being used, monitoring student progress is becoming a challenge. The paper answers two questions. The first one is how feasible is to monitor the learning activities occurring in a student personal workspace. The second is how to use the recorded data for the prediction of student achievement in a course. To address these research questions, the paper presents the use of virtual appliances, a fully functional computer simulated over a regular one and configured with all the required tools needed in a learning experience. Students carry out activities in this environment in which a monitoring scheme has been previously configured. A case study is presented in which a comprehensive set of observations were collected. The data is shown to have significant correlation with student academic achievement thus validating the approach to be used as a prediction mechanism. Finally a prediction model is presented based on those observations with the highest correlation.