A Multi-fold Time Approach to Address Emotions in Live and Virtualized Collaborative Learning

The enrichment of Computer Supported Collaborative (CSCL) Systems with emotion awareness features (detect emotion patterns and respond effectively) opens a window to the future of learner-to-computer interaction. In the current paper we present a system's design that attempts to evaluate the learner's affective state while he/she is taking part into collaborative tasks, in three different time-points: (i) before the task, (ii) in real-time (while collaborating) and (iii) retrospective (after the task). For the emotion assessment process, self-reporting and sentiment analysis are explored. Based on effective production rules that correlate emotions or emotion sequences to affective feedback techniques, the system will provide emotion scaffolds corresponding to user needs and feelings.