Abstract
We explored the reliability of detecting a learner's affect from conversational features extracted from interactions with AutoTutor, an intelligent tutoring system (ITS) that helps students learn by holding a conversation in natural language. Training data were collected in a learning session with AutoTutor, after which the affective states of the learner were rated by the learner, a peer, and two trained judges. Inter-rater reliability scores indicated that the classifications of the trained judges were more reliable than the novice judges. Seven data sets that temporally integrated the affective judgments with the dialogue features of each learner were constructed. The first four datasets corresponded to the judgments of the learner, a peer, and two trained judges, while the remaining three data sets combined judgments of two or more raters. Multiple regression analyses confirmed the hypothesis that dialogue features could significantly predict the affective states of boredom, confusion, flow, and frustration. Machine learning experiments indicated that standard classifiers were moderately successful in discriminating the affective states of boredom, confusion, flow, frustration, and neutral, yielding a peak accuracy of 42% with neutral (chance = 20%) and 54% without neutral (chance = 25%). Individual detections of boredom, confusion, flow, and frustration, when contrasted with neutral affect, had maximum accuracies of 69, 68, 71, and 78%, respectively (chance = 50%). The classifiers that operated on the emotion judgments of the trained judges and combined models outperformed those based on judgments of the novices (i.e., the self and peer). Follow-up classification analyses that assessed the degree to which machine-generated affect labels correlated with affect judgments provided by humans revealed that human-machine agreement was on par with novice judges (self and peer) but quantitatively lower than trained judges. We discuss the prospects of extending AutoTutor into an affect-sensing ITS.
| Original language | English (US) |
|---|---|
| Pages (from-to) | 45-80 |
| Number of pages | 36 |
| Journal | User Modeling and User-Adapted Interaction |
| Volume | 18 |
| Issue number | 1-2 |
| DOIs | |
| State | Published - Feb 2008 |
| Externally published | Yes |
Fingerprint
Keywords
- Affect detection
- AutoTutor
- Conversational cues
- Dialogue features
- Discourse markers
- Human-computer dialogue
- Human-computer interaction
- Intelligent Tutoring Systems
ASJC Scopus subject areas
- Human-Computer Interaction
Cite this
Automatic detection of learner's affect from conversational cues. / D'Mello, Sidney K.; Craig, Scotty; Johnson, Amy; McDaniel, Bethany; Graesser, Arthur.
In: User Modeling and User-Adapted Interaction, Vol. 18, No. 1-2, 02.2008, p. 45-80.Research output: Contribution to journal › Article
}
TY - JOUR
T1 - Automatic detection of learner's affect from conversational cues
AU - D'Mello, Sidney K.
AU - Craig, Scotty
AU - Johnson, Amy
AU - McDaniel, Bethany
AU - Graesser, Arthur
PY - 2008/2
Y1 - 2008/2
N2 - We explored the reliability of detecting a learner's affect from conversational features extracted from interactions with AutoTutor, an intelligent tutoring system (ITS) that helps students learn by holding a conversation in natural language. Training data were collected in a learning session with AutoTutor, after which the affective states of the learner were rated by the learner, a peer, and two trained judges. Inter-rater reliability scores indicated that the classifications of the trained judges were more reliable than the novice judges. Seven data sets that temporally integrated the affective judgments with the dialogue features of each learner were constructed. The first four datasets corresponded to the judgments of the learner, a peer, and two trained judges, while the remaining three data sets combined judgments of two or more raters. Multiple regression analyses confirmed the hypothesis that dialogue features could significantly predict the affective states of boredom, confusion, flow, and frustration. Machine learning experiments indicated that standard classifiers were moderately successful in discriminating the affective states of boredom, confusion, flow, frustration, and neutral, yielding a peak accuracy of 42% with neutral (chance = 20%) and 54% without neutral (chance = 25%). Individual detections of boredom, confusion, flow, and frustration, when contrasted with neutral affect, had maximum accuracies of 69, 68, 71, and 78%, respectively (chance = 50%). The classifiers that operated on the emotion judgments of the trained judges and combined models outperformed those based on judgments of the novices (i.e., the self and peer). Follow-up classification analyses that assessed the degree to which machine-generated affect labels correlated with affect judgments provided by humans revealed that human-machine agreement was on par with novice judges (self and peer) but quantitatively lower than trained judges. We discuss the prospects of extending AutoTutor into an affect-sensing ITS.
AB - We explored the reliability of detecting a learner's affect from conversational features extracted from interactions with AutoTutor, an intelligent tutoring system (ITS) that helps students learn by holding a conversation in natural language. Training data were collected in a learning session with AutoTutor, after which the affective states of the learner were rated by the learner, a peer, and two trained judges. Inter-rater reliability scores indicated that the classifications of the trained judges were more reliable than the novice judges. Seven data sets that temporally integrated the affective judgments with the dialogue features of each learner were constructed. The first four datasets corresponded to the judgments of the learner, a peer, and two trained judges, while the remaining three data sets combined judgments of two or more raters. Multiple regression analyses confirmed the hypothesis that dialogue features could significantly predict the affective states of boredom, confusion, flow, and frustration. Machine learning experiments indicated that standard classifiers were moderately successful in discriminating the affective states of boredom, confusion, flow, frustration, and neutral, yielding a peak accuracy of 42% with neutral (chance = 20%) and 54% without neutral (chance = 25%). Individual detections of boredom, confusion, flow, and frustration, when contrasted with neutral affect, had maximum accuracies of 69, 68, 71, and 78%, respectively (chance = 50%). The classifiers that operated on the emotion judgments of the trained judges and combined models outperformed those based on judgments of the novices (i.e., the self and peer). Follow-up classification analyses that assessed the degree to which machine-generated affect labels correlated with affect judgments provided by humans revealed that human-machine agreement was on par with novice judges (self and peer) but quantitatively lower than trained judges. We discuss the prospects of extending AutoTutor into an affect-sensing ITS.
KW - Affect detection
KW - AutoTutor
KW - Conversational cues
KW - Dialogue features
KW - Discourse markers
KW - Human-computer dialogue
KW - Human-computer interaction
KW - Intelligent Tutoring Systems
UR - http://www.scopus.com/inward/record.url?scp=38749099104&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=38749099104&partnerID=8YFLogxK
U2 - 10.1007/s11257-007-9037-6
DO - 10.1007/s11257-007-9037-6
M3 - Article
VL - 18
SP - 45
EP - 80
JO - User Modeling and User-Adapted Interaction
JF - User Modeling and User-Adapted Interaction
SN - 0924-1868
IS - 1-2
ER -