Year: 2007
Type: article
Abstract: This research demonstrates the utility of automatically monitoring a student's posture to track the affective states of boredom (low engagement) and flow (high engagement), which have been shown to influence learning.After a tutoring session with AutoTutor, the affective states of the student were rated by the learner, a peer, and two trained judges.Our results indicated that the affective state of flow was manifested through heightened pressure exerted on the seat of a pressure sensitive chair.Boredom, in turn, was associated with an increase in the pressure exerted on the back coupled with a rapid change in pressure on the seat, perhaps indicative of a state of restlessness.We also investigated the diagnosticity of each of the posture features and the reliability of a computer automatically discriminating episodes of boredom versus flow, which is a major discrimination in any affect-sensitive tutoring system.
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
SDG: Quality education
Open Access status: green
OpenAlex ID: W161622524