Abstract
In this paper, we examine whether it is possible to automatically classify patterns of interactions using a state transition model and identify successful versus unsuccessful student Q&A discussions. For state classification, we apply Conditional Random Field and Hidden Markov Models to capture transitions among the states. The initial results indicate that such models are useful for modeling some of the student dialogue states. We also show the results of classifying threads as successful/unsuccessful using the state information.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Kim, J., Chem, G., Feng, D., Shaw, E., Hovy, E.: Mining and assessing discussions on the web through speech act analysis. Proceedings of the Workshop on Web Content Mining with Human Language Technologies at the 5th International Semantic Web Conference (2006)
Kang, J.H., Kim, J., Shaw, E.: Modeling Successful versus Unsuccessful Threaded Discussions. In: Workshop on Opportunities for Intelligent and Adaptive Behavior in Collaborative Learning Systems, vol. 13 (2010)
Kang, J., Kim, J.: Profiling Message Roles in Threaded Discussions using an Influence Network Model, internal project report (2010)
Drummond, J., Kim, J.: Role of Elaborated Answers on Degrees of Student Participation in an Online Question-Answer. American Educational Research Association (2011)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Seo, S.W., Kang, JH., Drummond, J., Kim, J. (2011). Using Graphical Models to Classify Dialogue Transition in Online Q&A Discussions. In: Biswas, G., Bull, S., Kay, J., Mitrovic, A. (eds) Artificial Intelligence in Education. AIED 2011. Lecture Notes in Computer Science(), vol 6738. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-21869-9_98
Download citation
DOI: https://doi.org/10.1007/978-3-642-21869-9_98
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-21868-2
Online ISBN: 978-3-642-21869-9
eBook Packages: Computer ScienceComputer Science (R0)