Using Graphical Models to Classify Dialogue Transition in Online Q&A Discussions


Soo Won Seo, Jeon-Hyung Kang, Joanna Drummond and Jihie Kim

Paper type: 


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.


Student online discussions, Q&A discussion classification