Please use this identifier to cite or link to this item: https://repository.isls.org/handle/1/2928
Title: Recognizing creative thinking in graphical e-discussions using artificial intelligence graph-matching techniques
Authors: Wegerif, Rupert
McLaren, Bruce
Chamrada, Marian
Scheuer, Oliver
Mansour, Nasser
Mikšátko, Jan
Issue Date: Jun-2009
Publisher: International Society of the Learning Sciences (ISLS)
Citation: Wegerif, R., McLaren, B., Chamrada, M., Scheuer, O., Mansour, N., & Mikšátko, J. (2009). Recognizing creative thinking in graphical e-discussions using artificial intelligence graph-matching techniques. In O'Malley, C., Suthers, D., Reimann, P., & Dimitracopoulou, A. (Eds.), Computer Supported Collaborative Learning Practices: CSCL2009 Conference Proceedings (pp. 108-112). Rhodes, Greece: International Society of the Learning Sciences.
Abstract: Many approaches to analyzing online argumentation focus on explicit reasoning and overlook the creative emergence of new ideas. The value of a dialogic analytic framework including creative emergence was tested through applying it to the coding and analysis of undergraduate synchronous e-discussions using a graphical interface within the EU funded project ARGUNAUT. Qualitative analysis found that critical reasoning functioned to `deepen' the graph through unpacking assumptions whilst creative emergence of new perspectives produced `widening' moves. This distinction between deepening and widening was successfully used as the basis for an artificial intelligence (AI) graph-matching algorithm. Given examples of deepening and widening from real e-discussions, the AI algorithm was able to successfully find other occurrences of such moves within new e-discussions. This supports our claim to distinguish between these two aspects of shared thinking and has the potential to provide awareness indicators as a support for e-moderation.
URI: https://doi.dx.org/10.22318/cscl2009.1.108
https://repository.isls.org//handle/1/2928
Appears in Collections:CSCL 2009

Files in This Item:
File SizeFormat 
108-112.pdf259.77 kBAdobe PDFView/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.