Invited Speakers
Data-based Student Modeling in Exploratory Learning Environments
Cristina Conati
Computing Science Department & Laboratory for Computational Intelligence, University of British Columbia [homepage]
Abstract: Exploratory Learning Environments (ELE) are designed to help users acquire knowledge by freely experiencing a target domain. In this setting, it is often hard to identify interaction behaviours that are conducive to learning, vs. behaviours that indicate student confusion, making it hard to provide adaptive support to students who do not learn well with ELEs. In this talk, I will present our work on using data-based approaches to identify and recognize revelant behavioral patterns during interaction with ELEs, with the goal of enabling ELEs to monitor how a student works with the environment and provide adaptive support when needed.
[Download the presentation slides (~1MB PDF)]
Social Network Analysis for the Assessment of Learning
Osmar Zaiane, Department of Computing Science, University of Alberta [homepage]
Abstract: Using computer-supported collaborative learning tools, learners interact forming relationships and complex flows of information. In a forum with very few learners it is customary to quickly collect thousands of messages in few months, and these are interrelated in intricate discussion threads. Assessing the participation and interaction between learners can become a daunting task. Social network analysis is a field of study attempting to understand and measure relationships between entities in networked information. Can social network analysis techniques and data mining techniques for information networks help examine and assess online interactions? We examine some work done in this area, particularly the application of community mining, and discuss some open problems pertaining to social network analysis in the e-learning domain.