A State Transition Model for Student Online Discussions

Discussion boards, or online asynchronous discussions, have become increasing popular course tools for university-level engineering courses. As a step towards assessing student learning in online discussion, we are investigating whether it is possible to characterize successful versus unsuccessful question and answer (Q&A) type discussions. We use a four-state model in identifying different stages of the Q&A dialogue. 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 four-state model 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.