The aim of the CEEGE project is to experimentally evaluate and compare current theories for mental modeling of problem solving and attention, as well as to refine and evaluate techniques for observing the physiological reactions of humans to situations that inspire pleasure, displeasure, arousal, dominance and fear. To reach this aim we model visual attention, expertise, emotional states and mental representation structures of chess players by collecting and analyzing multi-modal data which allow us to build computational models. We collect multi-modal data from experiments of eye-tracking, structural dimensional analysis of mental representation (SDA-M), response to priming effects and physiological response of chess players during the game.
Primary impacts will be improved scientific understanding in the disciplines of Computer Science and Cognitive Neuro-Science.
Especially, this project will allow us to address the following research challenges:
- To what extent is it possible to use patterns of eye-scan and facial expressions to discover and model the understanding of a person during problem-solving?
- Are new techniques of deep learning more effective than traditional techniques for modeling the mental representations and predicting actions of subjects?
- What are the most effective techniques to observe and represent the emotional reaction of subjects from face expressions and body movements.
Possible applications include context aware systems, affective computing and new forms of human computer interaction, as well as software for interactive training of chess players which allows a differentiated feedback via eye-tracking and body parameters and based on our implemented MLN network the analysis of players’ expertise due to different key motifs and different phases of chess games: development of an individualized, adaptive chess assistance system for scaffolding cognitive, emotional and attentive chess learning.