Automatic prediction of frustration
International Journal of Human-Computer Studies
Toward an Affect-Sensitive AutoTutor
IEEE Intelligent Systems
Automatic Detection of Learner's Affect From Gross Body Language
Applied Artificial Intelligence
Affect Detection: An Interdisciplinary Review of Models, Methods, and Their Applications
IEEE Transactions on Affective Computing
ACII'11 Proceedings of the 4th international conference on Affective computing and intelligent interaction - Volume Part I
Automatic Recognition of Non-Acted Affective Postures
IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
Mood Meter: large-scale and long-term smile monitoring system
ACM SIGGRAPH 2012 Emerging Technologies
Comparing four technologies for measuring postural micromovements during monitor engagement
Proceedings of the 30th European Conference on Cognitive Ergonomics
| Hi-index | 0.00 |
Discrete, three-minute, computer-presented stimuli (designed to range from engaging to incredibly boring) were used to elicit changes in cognitive/emotional states in seated, healthy volunteers. These stimuli did not require the use of a mouse, so movements were assumed to be non- instrumental. Stimuli included films, games, quizzes and music. Motion capture and video analysis were used to detect changes in head and shoulder position in response to the stimuli. Results include changes occurring between the first half and the second half of each of the main stimuli (i.e. arising in less than one minute as the volunteer "settles in"); in the second half of each stimulus, there were decreases in head height and shoulder height (i.e. position rather than movement). In conclusion, we speculate that non-instrumental changes in head height and shoulder height may suggest loss of vigilance or diminishing arousal in seated computer-users. Our unique contributions are: 1) discrete stimuli, were used on seated volunteers 2) without a mouse, to show that 3) modest (mm) head and shoulder movements in the vertical axis correlated with 4) subtle cyclical changes in boredom, not overall changes in fatigue. Future psychological validation of tutoring systems with discrete stimuli can use these postural parameters as part of a multimodal analysis of engagement.