Publication Information

Authors:

• Jeanine A. DeFalco, Columbia University
• Jonathan P Rowe, North Carolina State University
• Luc Paquette, Teachers College, Columbia University
• Vasiliki Georgoulas-Sherry, Columbia University
• Keith Brawner,
• Bradford W. Mott, North Carolina State University
• Ryan S.J.D Baker, Columbia University
• James Lester, North Carolina State University

Pages:

• 152-193

Keywords:

• Affect detection, Motivational feedback, Game-based learning, Gift

Abstract:

• Tutoring systems that are sensitive to affect show considerable promise for enhancing student learning experiences. Creating successful affective responses requires considerable effort both to detect student affect and to design appropriate responses to affect. Recent work has suggested that affect detection is more effective when both physical sensors and interaction logs are used, and that context-sensitive design of affective feedback is necessary to enhance engagement and improve learning. In this paper, we provide a comprehensive report on a multi-part study that integrates detection, validation, and intervention into a unified approach. This paper examines the creation of both sensor-based and interaction-based detectors of student affect, producing successful detectors of student affect. In addition, it reports results from an investigation of motivational feedback messages designed to address student frustration, and investigates whether linking these interventions to detectors improves outcomes. Our results are mixed, finding that self-efficacy enhancing interventions based on interaction-based affect detectors enhance outcomes in one of two experiments investigating affective interventions. This work is conducted in the context of the GIFT framework for intelligent tutoring, and the TC3Sim game-based simulation that provides training for first responder skills.