Automatic support for the analysis of online collaborative learning chat conversations

Authors:
Stefan Trausan-Matu
Affiliations:
University "Politehnica" of Bucharest, Department of Computer Science and Engineering, Bucharest, Romania and Research Institute for Artificial Intelligence of the Romanian Academy, Bucharest, Rom ...
Venue:
ICHL'10 Proceedings of the Third international conference on Hybrid learning
Year:
2010

Citing 8
Cited 0

Toward a dialogic theory of learning: Bakhtin's contribution to understanding learning in settings of collaboration

CSCL '99 Proceedings of the 1999 conference on Computer support for collaborative learning
Group Cognition: Computer Support for Building Collaborative Knowledge (Acting with Technology)

Group Cognition: Computer Support for Building Collaborative Knowledge (Acting with Technology)
Speech and Language Processing (2nd Edition)

Speech and Language Processing (2nd Edition)
Extraction of Socio-semantic Data from Chat Conversations in Collaborative Learning Communities

EC-TEL '08 Proceedings of the 3rd European conference on Technology Enhanced Learning: Times of Convergence: Technologies Across Learning Contexts
The Language Technologies for Lifelong Learning Project

ICALT '09 Proceedings of the 2009 Ninth IEEE International Conference on Advanced Learning Technologies
Overview and preliminary results of using polyCAFe for collaboration analysis and feedback generation

EC-TEL'10 Proceedings of the 5th European conference on Technology enhanced learning conference on Sustaining TEL: from innovation to learning and practice
Studying Virtual Math Teams

Studying Virtual Math Teams
A polyphonic model and system for inter-animation analysis in chat conversations with multiple participants

CICLing'10 Proceedings of the 11th international conference on Computational Linguistics and Intelligent Text Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

The paper starts from experiments of using online instant messenger chats as an assignment in a classical face to face course. Tutors reported that the activity of evaluating and grading students' chats is very difficult. Starting from the analysis of their evaluations, Bakhtin's polyphonic theory was chosen as a good starting point for developing automatic support tools. As a consequence, the PolyCAFe system based on this theory was developed using techniques from Natural Language Processing and Social Network Analysis. The system provides interactive graphics visualization of the chat and textual feedback. The persons who will beneficiate the most from the system are tutors. They can use the system for analyzing the participation of students and getting insights for writing a detailed feedback and grading. Students also may use the system, for getting feedback.