Domain Knowledge and Adaptive Serious Games: Exploring the Relationship of Learner Ability and Affect Adaptability. (April 2022)

• Record Type: Journal Article
• Authors: Verma, Vipin; Craig, Scotty D.; Levy, Roy; Bansal, Ajay; Amresh, Ashish
• Is Part Of: Journal of educational computing research. Volume 60:Number 2(2022)
• Page Start: 406
• Page End: 432
• Publication Date: 2022-04
• Subjects: affect-sensitive -- quantitative -- learning environments -- games -- interactive -- technology -- assessment -- artificial intelligence -- serious game -- boredom -- flow -- frustration; Computer literacy -- Periodicals; Computer-assisted instruction -- Periodicals; Computer managed instruction -- Periodicals; Education -- Data processing -- Periodicals; 371.334
• DOI: 10.1177/07356331211031287
• Languages: English
• ISSNs: 0735-6331

Abstract

Detection and responding to a player's affect are important for serious games. A method for this purpose was tested within Chem-o-crypt, a game that teaches chemical equation balancing. The game automatically detects boredom, flow, and frustration using the Affdex SDK from Affectiva. The sensed affective state is then used to adapt the game play in an attempt to engage the player in the game. A randomized controlled experiment incorporating a Dynamic Bayesian Network that compared results from groups with the affect-sensitive states vs those without revealed that measuring affect and adapting the game improved learning for low domain-knowledge participants.