NotesFAQContact Us
Collection
Advanced
Search Tips
ERIC Number: ED536318
Record Type: Non-Journal
Publication Date: 2012
Pages: 8
Abstractor: ERIC
Reference Count: 12
ISBN: N/A
ISSN: N/A
EEG Estimates of Cognitive Workload and Engagement Predict Math Problem Solving Outcomes
Beal, Carole R.; Galan, Federico Cirett
Society for Research on Educational Effectiveness
In the present study, the authors focused on the use of electroencephalography (EEG) data about cognitive workload and sustained attention to predict math problem solving outcomes. EEG data were recorded as students solved a series of easy and difficult math problems. Sequences of attention and cognitive workload estimates derived from the EEG signals were used to train a Support Vector Machine ([SVM], a machine learning classifier) to predict the outcome of the problem: correct or incorrect answer. The authors were also interested in learning if the EEG estimates would be different for easy and hard problems, as suggested by the results of Chaouachi et al. (2011), and if the estimates would be related to the students' self-report of how difficult the problem was. The preliminary results suggest that using the estimates of Engagement and Workload from EEG data can predict problem solving outcomes better than the base rate of performance on the problems. In general, predictions that utilized both signal sources tended to be better, although this was not consistently observed. Predictions were somewhat better for easy problems, perhaps because students solved those items more quickly; prediction accuracy tends to decline with the amount of time the student works on the problem, perhaps due to increased noise in the sensor data streams. Overall, the results were consistent with other recent studies suggesting that the application of neuroscience methods may be a valuable addition to education research. (Contains 2 tables.)
Society for Research on Educational Effectiveness. 2040 Sheridan Road, Evanston, IL 60208. Tel: 202-495-0920; Fax: 202-640-4401; e-mail: inquiries@sree.org; Web site: http://www.sree.org
Publication Type: Reports - Research
Education Level: Higher Education
Audience: N/A
Language: English
Sponsor: N/A
Authoring Institution: Society for Research on Educational Effectiveness (SREE)