We employ a multimodal Hidden Markov Model (HMM) based methodology
to investigate the temporal learning processes of two types of learners that have
learning gains and a type that does not have learning gains in an open-ended
collaborative learning activity.
We make use of our open-source dataset. We consider log data, speech behavior, affective
states and gaze patterns for each team for time windows of 10 seconds in a non-incremental format.
The libraries we use for this methodology are listed in requirements.txt.
src: contains an analysis notebook for each of the learner types.results: contains the reference result notebooks referred to in the paper.