Towards Predicting Attention and Workload During Math Problem Solving
Gifted students are characterized by a low level of attention and workload. Thus, it is very important to detect the variation of these values in real time when children are solving problems. A low value of workload or attention could be an indicator that the child is gifted. In this paper, we conducted a preliminary study in order to detect when children have a low values of attention or workload. A sample of 17 pupils participated in this study by solving math problems in an environment called Netmath. The EEG signal data collected from the experiment was used to train a Long Short Term Memory network (LSTM) to predict two mental states (attention and workload) in real time, when solving math problem. First results show that it is possible to predict these values in real time and the accuracy of the prediction is slightly above the random model. This pilot research provide some insight to the hypothesis that we can predict those variables in real time, which might be useful to intelligent tutor and to detect gifted children.
KeywordsElectroencephalography (EEG) prediction LSTM Attention Workload
We would like to thanks The Fonds de recherche du Québec – Nature et technologies (FRQNT) for their financial support and Beam Me Up Games.
- 1.Beal, C.R., Galan, F.C.: EEG estimates of cognitive workload and engagement predict math problem solving outcomes. Soc. Res. Educ. Eff. Consultado el, 05/17/19 (2012). http://eric.ed.gov/?q=EEG&id=ED536318
- 4.Chang, K.M., Nelson, J., Pant, U., Mostow, J.: Toward exploiting EEG input in a reading tutor. Int. J. Artif. Intell. Educ. 22(1–2), 19–38 (2013)Google Scholar
- 5.Chaouachi, M., Jraidi, I., Frasson, C.: Adapting to learners’ mental states using a physiological computing approach. In: FLAIRS Conference, pp. 257–262 (2015)Google Scholar
- 6.Davis, G.A., Rimm, S.B.: Education of the Gifted and Talented. Prentice-Hall, Inc., Upper Saddle River (1989)Google Scholar
- 7.Ghali, R., Abdessalem, H.B., Frasson, C., Nkambou, R.: Identifying brain characteristics of bright students. J. Intell. Learn. Syst. Appl. 10(03), 93 (2018)Google Scholar
- 9.Murdoch, W.J., Szlam, A.: Automatic rule extraction from long short term memory networks. arXiv preprint arXiv:1702.02540 (2017)
- 10.Renzulli, J.S.: The Three-Ring Conception of Giftedness: A Developmental Model for Promoting Creative Productivity. Cambridge University Press, Cambridge (2005)Google Scholar
- 13.Tai, K.S., Socher, R., Manning, C.D.: Improved semantic representations from tree-structured long short-term memory networks. arXiv preprint arXiv:1503.00075 (2015)
- 14.Terman, L.M., Baldwin, B.T., Bronson, E., De Voss, J.C.: Mental and Physical Traits of a Thousand Gifted Children, vol. 1. Stanford University Press, Stanford (1926)Google Scholar
- 15.Xu, K., et al.: Show, attend and tell: neural image caption generation with visual attention. In: International Conference on Machine Learning, pp. 2048–2057 (2015)Google Scholar
- 16.Zaremba, W., Sutskever, I.: Learning to execute. arXiv preprint arXiv:1410.4615 (2014)