CALA Workshop

Workshop on “Computational Aspects of Learning Analytics”

Dept. of Computer Science and Applied Cognitive Science
Campus Duisburg, LF 310 (Rotunde), Thursday, April 19, 9:15-12:30

Interaction, Mediation, and Ties:
A Framework for Multi-Level Analysis of Distributed Interaction


Professor Dan SuthersProf. Daniel D. Suthers
University of Hawaii

Learning and knowledge creation is often distributed across multiple media and sites in networked environments. Traces of such activity may be fragmented across multiple logs and may not match analytic needs, obscuring the coherence of distributed interaction. Understanding distributed learning and knowledge creation requires multi-level analysis of small group activity and of how this local activity gives rise to larger phenomena in a network. In response to these needs, we have developed an abstract transcript representation that provides a unified analytic artifact of distributed activity, and an analytic hierarchy that supports multiple levels of analysis, including models of interaction, mediated associations, and ties. The presentation describes the analytic hierarchy, summarizes several current research efforts that use this framework, and discusses further areas of work.
Download presentation
More information about the author

A Polyphonic Model and System for Interaction Analysis in Collaborative Learning


Professor Stefan Trausan-MatuProf. Stefan Trausan-Matu
Romanian Academy of Sciences, Bucarest

The talk presents the polyphonic model of interactions in Computer-Supported Collaborative Learning (CSCL), which focuses on the inter-animation of multiple voices (in a generalized sense), which sometimes weave in a polyphonic, counterpointal threading. The model may be applied to conversations, discussion forums, essays and even non-verbal interactions. A series of systems were developed starting from the polyphony ideas, offering facilities for voices' graphical visualizations. The most elaborated is PolyCAFe, implemented with techniques from Natural Language Processing and Social Network Analysis in order to detect and providing feedback about the content of the contributions and the involvement (inter-animation) of the participants.
Download presentation
More information about the author

Using Network Analysis in the Context of Technology-Enhanced Learning


Professor Ulrich HoppeProf. H. Ulrich Hoppe
University of Duisburg-Essen

In the area of computer-supported collaborative learning (CSCL), the methodology of social network analysis (SNA) has gained considerable attention. It has been used to identify roles and internal structures in learning groups and is an important tool to provide information and insight for managing learning communities. From the more general point of view of "network science", the model of scale-free networks based on the mechanism of "preferential attachment" explains important characteristics in the evolution of real-world networks. It will be shown that these models and analytic mechanisms are also relevant in various areas of technology-enhanced learning with examples taken from concept mapping as well as from learning and competence development in online communities of practice.
Download presentation
More information about the author

Theme by Danetsoft and Danang Probo Sayekti inspired by Maksimer