Gaining Insight by Transforming Between Temporal Representations of Human Interaction
Recordings of human interaction data can be organized into temporal representations with different affordances. We use audio data of a learning-related discussion analyzed for its low-level emotional indicators and divided into four phases, each characterized by an overarching emotion. After arguing for the relevance of emotion to learning, we examine this original analysis with the help of three different representations, transforming the data between them in order to connect micro- and macro-levels of analysis and give meaning to these connections. The first is a FRIEZE representation showing the temporal distribution of the low-level indicators of emotion as well as the phases. The second is an epistemic network analysis with an aggregated representation that shows how the pattern of associations among indicators of emotion differs between phases. The third is a transcription of the original data that re-anchors the aggregation back into the temporal interaction, giving it meaning. This is a methods paper, and if the findings are not specifically focused on measuring learning, the data do concern a student narrative of interactions with her teacher. More importantly, the stage is set for giving meaning to micro- and macro-connections in pedagogical contexts, with a view to automated analyses.