Journal of Learning Analytics
Society for Learning Analytics Research
Analyses of learning based on student discourse need to account not only for the content of the utterances but also for the ways in which students make connections across turns of talk. This requires segmentation of discourse data to define when connections are likely to be meaningful. In this paper, we present an approach to segmenting data for the purposes of modeling connections in discourse using epistemic network analysis. Specifically, we use epistemic network analysis to model connections in student discourse using a temporal segmentation method adapted from recent work in the learning sciences. We compare the results of this study to a purely conversation-based segmentation method to examine the affordances of temporal segmentation for modeling connections in discourse.
Siebert-Evenstone, A. L., Arastoopour Irgens, G., Collier, W., Swiecki, Z., Ruis, A. R., & Williamson Shaffer, D. (2017). In Search of Conversational Grain Size: Modeling Semantic Structure using Moving Stanza Windows. Journal of Learning Analytics, 4(3), 123–139. https://doi.org/10.18608/jla.2017.43.7