Please use this identifier to cite or link to this item:
Title: Enabling automatic just-in-time evaluation of in-class discussions in on-line collaborative learning practices
Author: Caballé Llobet, Santi  
Lapedriza García, Àgata
Masip Rodó, David
Xhafa, Fatos
Abraham, Ajith
Others: Universitat Oberta de Catalunya (UOC)
Universitat Politècnica de Catalunya
Norwegian University of Science and Technology
Keywords: collaborative learning
knowledge discovery
automatic evaluation
machine learning
Issue Date: Oct-2009
Publisher: Journal of Digital Information Management
Citation: Caballé, S., Lapedriza, A., Masip, D., Xhafa, F. & Abraham, A. (2009). Enabling Automatic Just-in-time Evaluation of In-class Discussions in On-line Collaborative Learning Practices. Journal of Digital Information Management, 7(5), 290-297.
Project identifier: info:eu-repo/grantAgreement/TIN2008-01288/TSI
Abstract: Learning by discussion when applied to on-line collaborative learning settings can provide signifi cant benefits for students in education in general. Indeed, the discussion process plays an important social task in collaborative learning practices. Participants can discuss about the activity being performed, collaborate with each other through the exchange of ideas that may arise, propose new resolution mechanisms, justify and refi ne their own contributions, and as a result, acquire new knowledge. Considering these benefits, current educational organizations incorporate on-line discussions into web-based courses as part of the very rationale of their pedagogical models. However, in-class collaborative assignments are usually greatly participated and contributed, which makes the monitoring and assessment tasks by tutors and moderators time-consuming, tedious and error-prone. Specially hard if not impossible by human tutors is to manually deal with the sequences of hundreds of contributions making up the discussion threads and the relations between these contributions. Consequently, tutoring tasks during on-line discussions usually restrict to offer evaluation results of the contributing effort and quality after the collaborative learning activity takes place and thus neglect the essential issue of constantly considering the process of knowledge building while it is still being performed. In this paper, we propose a multidimensional model based on data analysis from online collaborative discussion interactions that provides a first step towards an automatic evaluation in just-in-time fashion. The context of this study is a real on-line discussion experience that took place at the Open University of Catalonia.
Language: English
ISSN: 0972-7272MIAR
Appears in Collections:Articles

Files in This Item:
File SizeFormat 
Caballe_JDIM_Enabling_Automatic.pdf205.1 kBAdobe PDFView/Open

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