Diagrammatic Student Models: Modeling Student Drawing Performance with Deep Learning
Recent years have seen a growing interest in the role that student drawing can play in learning. Because drawing has been shown to contribute to students’ learning and increase their engagement, developing student models to dynamically support drawing holds significant promise. To this end, we introduce diagrammatic student models, which reason about students’ drawing trajectories to generate a series of predictions about their conceptual knowledge based on their evolving sketches. The diagrammatic student modeling framework utilizes deep learning, a family of machine learning methods based on a deep neural network architecture, to reason about sequences of student drawing actions encoded with temporal and topological features. An evaluation of the deep-learning-based diagrammatic student models suggests that it can predict student performance more accurately and earlier than competitive baseline approaches.
KeywordsStudent modeling Intelligent tutoring systems Deep learning
Unable to display preview. Download preview PDF.
- 5.Zhang, H., Linn, M.: Using drawings to support learning from dynamic visualizations. In: Proceedings of the 8th International Conference of the Learning Sciences, Utrecht, The Netherlands, pp. 161–162 (2008)Google Scholar
- 13.Min, W., Ha, E.Y., Rowe, J.P., Mott, B.W., Lester, J.C.: Deep learning-based goal recognition in open-ended digital games. In: Tenth Artificial Intelligence and Interactive Digital Entertainment Conference, Raleigh, NC, pp. 37–43 (2014)Google Scholar
- 14.Valentine, S., Vides, F., Lucchese, G., Turner, D., Kim, H., Li, W., Linsey, J., Hammond, T.: Mechanix: a sketch-based tutoring system for statics courses. In: Proceedings of the Twenty-Fourth Conference on Innovative Applications of Artificial Intelligence, Toronto, Ontario, Canada (2012)Google Scholar
- 16.Jee, B., Gentner, D.: Drawing on experience: use of sketching to evaluate knowledge of spatial scientific concepts. In: Proceedings of the 31st Annual Conference of the Cognitive Science Society, Amsterdam, The Netherlands (2009)Google Scholar
- 18.Wiebe, E.N., Madden, L.P., Bedward, J.C., Carter, M.: Examining Science Inquiry Practices in the Elementary Classroom through Science Notebooks. Presented at NARST Annual Meeting, Garden Grove (2009)Google Scholar
- 19.Smith, A., Wiebe, E., Mott, B., Lester, J.: SketchMiner: mining learner-generated science drawings with topological abstraction. In: Proceedings of the Seventh International Conference on Educational Data Mining, London, UK, pp. 288–291 (2014)Google Scholar
- 20.Bengio, Y., Lamblin, P.: Greedy Layer-wise Training of Deep Networks. Advances in neural information processing systems 19, 153 (2007)Google Scholar
- 21.Krizhevsky, A., Sutskever, I., Hinton, G.: Imagenet classification with deep convolutional neural networks. In: Advances in neural information processing systems, pp. 1097–1105 (2012)Google Scholar
- 22.Socher, R., Pennington, J., Huang, E.: Semi-supervised recursive autoencoders for predicting sentiment distributions. In: Linguistics, A. for C. (ed.) Proceedings of the Conference on Empirical Methods in Natural Language Processing, pp. 151–161 (2011)Google Scholar
- 24.Palm, R.: Prediction as a candidate for learning deep hierarchical models of data. Technical University of Denmark. (2012)Google Scholar
- 25.Hsu, C., Chang, C., Lin, C.: A Practical Guide to Support Vector Classification. 1, 1–16 (2003)Google Scholar
- 26.Blaylock, N., Allen, J.: Hierarchical Goal Recognition. Plan, Activity, and Intent Recognition Theory and Practice, pp. 3–31 (2014)Google Scholar