Assessing the dialogic properties of classroom discourse: Proportion models for imbalanced classes
Automatic assessment of dialogic properties of classroom discourse would benefit several widespread classroom observation protocols. However, in classrooms with low incidences of dialogic discourse, assessment can be highly biased against detecting dialogic properties. In this paper, we present an approach to addressing this imbalanced class problem. Rather than perform classifications at the utterance level, we aggregate feature vectors to classify proportions of dialogic properties at the class-session level and achieve a moderate correlation with actual proportions, r(130) = .50, p < .001, CI95[.36,.61] . We show that this approach outperforms aggregating utterance level classifications, r(130) = .27, p = .001, CI95[.11,.43], is stable for both low and high dialogic classrooms, and is stable across both automatic speech recognition and human transcripts.
Proceedings of the 10th International Conference on Educational Data Mining, EDM 2017
Olney, A., Samei, B., Donnelly, P., & D’Mello, S. (2017). Assessing the dialogic properties of classroom discourse: Proportion models for imbalanced classes. Proceedings of the 10th International Conference on Educational Data Mining, EDM 2017, 162-167. Retrieved from https://digitalcommons.memphis.edu/facpubs/7421