Argunaut Highlights...

In this part of the website, we highlight some important aspects of our project. We provide a brief description and further reading options.

• Cross-System Interoperability and the Moderator's Interface
• Meaningful indicators for e-discussions
• Argunaut's theoretical perspectives regarding the evaluation of discussions and moderation practices

Cross-System Interoperability and the Moderator's Interface

The Argunaut system is designed to achieve interoperability, that is to say, serve more than one e-discussion end user environment (EUE). Since actions, objects and users are logged differently across e-discussion tools, there was a need for a "common format", a unified representation schema for action logs from both EUEs handled by the project, which can also be applied to other types of e-discussion logs. This was achieved via the use of transformational approaches converting the action logging of the EUEs to common format XML logs.

The Argunaut 'Moderator's Interface' includes a unified graphical representation and a cross-system replay system based on this common format, which allows the moderators to monitor the discussion in progress, regardless of the concrete EUE the students are using. It also includes the ability to make content keyword queries, annotate discussions, and intervene in the students' EUEs via remote control capabilities.

Further reading:

• De Groot, R., Drachman, R., Hever, R., Schwarz, B.B., Hoppe, U., Harrer, A., De Laat, M., Wegerif, R., McLaren, B.M., & Baurens, B. (2007). Computer Supported Moderation of E-Discussions: the ARGUNAUT Approach. In: Mice, Minds, and Society – The Computer Supported Collaborative Learning (CSCL) Conference 2007, ed. by Clark Chinn and Gijsbert Erkens and Sadhana Puntambekar, vol. 8, pp. 165-;167, International Society of the Learning Sciences.

Meaningful indicators for e-discussions

 Moderation of e-discussions can be facilitated by online feedback promoting awareness and understanding of the ongoing discussion. Toward achieving such feedback, we have focused on identifying and annotating phenomena relevant to the analysis and evaluation of e-discussions. Our initial experiences would suggest that actions, objects and attributes in the discussion log files, can be successfully used to capture more meaningful theoretical phenomena. This can be achieved by the combination of structural and process-oriented elements (e.g., ontologies of shapes, types of connectors, logged actions) with content elements (the text of the discussion itself). One direction for this is the training of machine-learning classifiers to classify discussion units (shapes and paired-shapes) into pre-defined theoretical categories, using structural and process-oriented attributes. The classifiers are trained with examples categorized by humans, based on content and some contextual cues. At this point we already have a few classifiers for phenomena such as 'critical reasoning' and 'question and answer', showing high overall accuracy (86-95%). A second direction is the use of a PROLOG-based pattern matching tool (Harrer, Vetter, Thür, & Brauckmann, 2005) in conjunction with e-discussion XML log files to generate "rules" in order to look for "patterns" that combine user actions (e.g., create shape, delete link) and structural elements with content key words.

 Further reading:

• Hever, R., De Groot, R., De Laat, M., Harrer, A., McLaren, B.M., & Scheuer, O. (2007). Combining Structural, Process-oriented and Textual Elements to Generate Awareness Indicators for Graphical E-discussions. In: Mice, Minds, and Society – The Computer Supported Collaborative Learning (CSCL) Conference 2007, ed. by Clark Chinn and Gijsbert Erkens and Sadhana Puntambekar, vol. 8, pp. 286-288, International Society of the Learning Sciences.
• McLaren, B. M., Scheuer, E., De Laat, M., Hever, R., De Groot, R., & Rose, C. P. (2007). Using Machine Learning Techniques to Analyze and Support Mediation of Student E-Discussions. In: Frontiers in Artificial Intelligence and Applications (vol. 158),  Artificial Intelligence in Education - Building Technology Rich Learning Contexts that Work, ed. by Rosemary Luckin and Kenneth R. Koedinger and Jim Greer, pp. 331-338, Amsterdam, IOS Press.
• Harrer, A., Hever, R., & Ziebarth, S. (2007). Empowering researchers to detect interaction patterns in electronic discussion and collaboration. In: Frontiers in Artificial Intelligence and Applications (vol. 158),  Artificial Intelligence in Education - Building Technology Rich Learning Contexts that Work, ed. by Rosemary Luckin and Kenneth R. Koedinger and Jim Greer, pp. 503-510, Amsterdam, IOS Press.

Argunaut's theoretical perspectives regarding the evaluation of discussions and moderation practices

The theoretical framework for Argunaut is a combination of several theoretical orientations. Firstly, we augment traditional argumentation theories with dialogic theory. Secondly, we integrate these with current understandings of teaching and moderating online. Finally, we situate them both within the paradigm of social learning, which influences how we frame collaborative learning and construction of knowledge. The integration of these three aspects made us realize that we needed a multi-dimensional analytical framework to look at our data. An argument ‘map’, which is our primary data, can be analyzed through a range of theoretical lenses. From the argumentation point of view one might focus on the quality of critical reasoning. Dialogic theory, as we have developed and applied it, focuses more on the multiplicity of perspectives and the creative emergence of new ways of seeing problems. Moderation aims to reflect on the impact of interventions made by the moderator to steer the discussion in a desired direction and social learning theories, in principle, focus on the level of participation and the conditions in which groups learn collectively. The analytical framework developed in this project aims to address and synthesize these different orientations in a meaningful way.

Further reading:

• De Laat, M., & Wegerif, R. (2007). Perspectives/rules to evaluate discussions. Argunaut public deliverable D5.1.
• Gil, J., Schwarz, B. B., & Asterhan, C. S. C. (2007). Intuitive moderation styles and beliefs of teachers in CSCL-based argumentation. In: Mice, Minds, and Society – The Computer Supported Collaborative Learning (CSCL) Conference 2007, ed. by Clark Chinn and Gijsbert Erkens and Sadhana Puntambekar, vol. 8, pp. 219-228, International Society of the Learning Sciences.