ABSTRACT
Sensor stream data, particularly those collected at the millisecond of granularity, have been notoriously difficult to leverage classifiable signal out of. Adding to the challenge is the limited domain knowledge that exists at these biological sensor levels of interaction that prohibits a comprehensive manual feature engineering approach to classification of those streams. In this paper, we attempt to enhance the assessment capability of a touchscreen based ratio tutoring system by using Recurrent Neural Networks (RNNs) to predict the strategy being demonstrated by students from their 60hz data streams. We hypothesize that the ability of neural networks to learn representations automatically, instead of relying on human feature engineering, may benefit this classification task. Our RNN and baseline models were trained and cross-validated at several levels on historical data which had been human coded with the task strategy believed to be exhibited by the learner. Our RNN approach to this historically difficult high frequency data classification task moderately advances performance above baselines and we discuss what implication this level of assessment performance has on enabling greater adaptive supports in the tutoring system.
- Ahsan Abdullah, Mohammad Adil, Leah Rosenbaum, Miranda Clemmons, Mansi Shah, Dor Abrahamson, and Michael Neff. 2017. Pedagogical Agents to Support Embodied, Discovery-Based Learning Intelligent Virtual Agents, Jonas Beskow, Christopher Peters, Ginevra Castellano, Carol O'Sullivan, Iolanda Leite, and Stefan Kopp (Eds.). Springer International Publishing, Cham, 1--14.Google Scholar
- Dor Abrahamson and Arthur Bakker. 2016. Making sense of movement in embodied design for mathematics learning. Cognitive Research: Principles and Implications Vol. 1, 1 (12. 2016), 1--13.Google ScholarCross Ref
- Ivon Arroyo, David G Cooper, Winslow Burleson, Beverly Park Woolf, Kasia Muldner, and Robert Christopherson. 2009. Emotion Sensors Go To School.. In AIED, Vol. Vol. 200. 17--24. Google ScholarDigital Library
- Paulo Blikstein. 2013. Multimodal learning analytics. In Proceedings of the third international conference on learning analytics and knowledge. ACM, 102--106. Google ScholarDigital Library
- Anthony F Botelho, Ryan S Baker, and Neil T Heffernan. 2017. Improving Sensor-Free Affect Detection Using Deep Learning International Conference on Artificial Intelligence in Education. Springer, 40--51.Google Scholar
- Franccois Chollet. 2015. keras. https://github.com/fchollet/keras.Google Scholar
- Abrahamson D., Lee R. G., Negrete A. G., and Gutiérrez J. F.. 2014. Coordinating visualizations of polysemous action: Values added for grounding proportion. In ZDM Mathematics Education, Visualization as an epistemological learning tool {Special issue}, F. Rivera, H. Steinbring, and A. Arcavi (Eds.). Vol. Vol. 46. 79--93.Google Scholar
- Abrahamson D., Shayan S., Bakker A., and Van der Schaaf M. F.. 2016. Eye-tracking Piaget: Capturing the emergence of attentional anchors in the coordination of proportional motor action. Human Development Vol. 58, 4--5 (2016), 218--244.Google Scholar
- Robin Devooght and Hugues Bersini. 2017. Long and Short-Term Recommendations with Recurrent Neural Networks Proceedings of the 25th Conference on User Modeling, Adaptation and Personalization (UMAP '17). ACM, New York, NY, USA, 13--21. Google ScholarDigital Library
- Klaus Greff, Rupesh K Srivastava, Jan Koutn'ık, Bas R Steunebrink, and Jürgen Schmidhuber. 2017. LSTM: A search space odyssey. IEEE transactions on neural networks and learning systems Vol. 28, 10 (2017), 2222--2232.Google Scholar
- Sepp Hochreiter and Jürgen Schmidhuber. 1997. Long short-term memory. Neural computation Vol. 9, 8 (1997), 1735--1780. Google ScholarDigital Library
- Mark Howison, Dragan Trninic, Daniel Reinholz, and Dor Abrahamson. 2011. The Mathematical Imagery Trainer: From Embodied Interaction to Conceptual Learning Proceedings of the SIGCHI Conference on Human Factors in Computing Systems (CHI '11). ACM, New York, NY, USA, 1989--1998. Google ScholarDigital Library
- Stephen Hutt, Caitlin Mills, Nigel Bosch, Kristina Krasich, James Brockmole, and Sidney D'Mello. 2017. "Out of the Fr-Eye-ing Pan": Towards Gaze-Based Models of Attention during Learning with Technology in the Classroom. (07. 2017), 94--103. Google ScholarDigital Library
- Lamon S. J.. 2007. Rational numbers and proportional reasoning: Toward a theoretical framework. In Second handbook of research on mathematics teaching and learning, F. Lester (Ed.). Charlotte, NC: Information Age Publishing, 629--668.Google Scholar
- Dietmar Jannach, Malte Ludewig, and Lukas Lerche. 2017. Session-based item recommendation in e-commerce: on short-term intents, reminders, trends and discounts. User Modeling and User-Adapted Interaction (2017), 1--42. Google ScholarDigital Library
- Antoine Lefebvre-Brossard, Alexandre Spaeth, and Michel C. Desmarais. 2017. Encoding User As More Than the Sum of Their Parts: Recurrent Neural Networks and Word Embedding for People-to-people Recommendation Proceedings of the 25th Conference on User Modeling, Adaptation and Personalization (UMAP '17). ACM, New York, NY, USA, 298--302. Google ScholarDigital Library
- LR Medsker and LC Jain. 2001. Recurrent neural networks. Design and Applications Vol. 5 (2001).Google Scholar
- Daniel Neil, Michael Pfeiffer, and Shih-Chi Liu. 2016. Phased LSTM: Accelerating Recurrent Network Training for Long or Event-based Sequences. In Advances in Neural Information Processing Systems 29, D. D. Lee, M. Sugiyama, U. V. Luxburg, I. Guyon, and R. Garnett (Eds.). Curran Associates, Inc, 3882--3890. Google ScholarDigital Library
- Chris Piech, Jonathan Bassen, Jonathan Huang, Surya Ganguli, Mehran Sahami, Leonidas J Guibas, and Jascha Sohl-Dickstein. 2015. Deep knowledge tracing. In Advances in Neural Information Processing Systems. 505--513. Google ScholarDigital Library
- George E. Raptis, Christina Katsini, Marios Belk, Christos Fidas, George Samaras, and Nikolaos Avouris. 2017. Using Eye Gaze Data and Visual Activities to Infer Human Cognitive Styles: Method and Feasibility Studies. In Proceedings of the 25th Conference on User Modeling, Adaptation and Personalization (UMAP '17). ACM, New York, NY, USA, 164--173. Google ScholarDigital Library
- MA Rau, HE Bowman, and JW Moore. 2016. Intelligent technology-support for collaborative connection-making among multiple visual representations in chemistry. Structure-Function Relationships in the Gas-Sensing Heme-Dependent Transcription Factors RcoM and DNR Vol. 1001 (2016), 178.Google Scholar
- Martina A Rau and Zachary A Pardos. 2016. Adding eye-tracking AOI data to models of representation skills does not improve prediction accuracy.. In EDM. 622--623.Google Scholar
- Alessandro Suglia, Claudio Greco, Cataldo Musto, Marco de Gemmis, Pasquale Lops, and Giovanni Semeraro. 2017. A Deep Architecture for Content-based Recommendations Exploiting Recurrent Neural Networks. In Proceedings of the 25th Conference on User Modeling, Adaptation and Personalization (UMAP '17). ACM, New York, NY, USA, 202--211. Google ScholarDigital Library
- Steven Tang, Joshua C Peterson, and Zachary A Pardos. 2017. Modelling Student Behavior using Granular Large Scale Action Data from a MOOC. The Handbook of Learning Analytics (2017), 223--233.Google Scholar
- Theano Development Team. 2016. Theano: A Python framework for fast computation of mathematical expressions. arXiv e-prints Vol. abs/1605.02688 (May. 2016). http://arxiv.org/abs/1605.02688Google Scholar
- Boyer T.W. and Levine S.C.. 2015. Prompting children to reason proportionally: Processing discrete units as continuous amounts. Developmental psychology Vol. 51, 5 (2015), 615--620.Google Scholar
Index Terms
- Classifying Learner Behavior from High Frequency Touchscreen Data Using Recurrent Neural Networks
Recommendations
EMG-based online classification of gestures with recurrent neural networks
Highlights- Gesture classification from Electromyography (EMG) signals.
- Evaluated on the ...
Graphical abstractDisplay Omitted
AbstractOnline gesture classification can rely on unsupervised segmentation in order to divide the data stream into static and dynamic segments for individual classification. However, this process requires motion detection calibration and adds ...
New Results for Prediction of Chaotic Systems Using Deep Recurrent Neural Networks
AbstractPrediction of nonlinear and dynamic systems is a challenging task, however with the aid of machine learning techniques, particularly neural networks, is now possible to accomplish this objective. Most common neural networks used are the multilayer ...
Deep Elman recurrent neural networks for statistical parametric speech synthesis
Owing to the success of deep learning techniques in automatic speech recognition, deep neural networks (DNNs) have been used as acoustic models for statistical parametric speech synthesis (SPSS). DNNs do not inherently model the temporal structure in ...
Comments