I am a Raleigh native who graduated from Duke University in 2005 with a double major in Electrical/Computer Engineering and Computer Science. Before returning to Raleigh to pursue a Ph.D. from NCSU, I worked for three years at SPAWAR Systems Center in San Diego, as part of their Unmanned Maritime Vehicles laboratory, focusing primarily on sensor integration/deployment for underwater gliders.
My research focuses on developing automated techniques for analyzing student drawings, and using deep learning to develop predictive student models of student performance using data collected from a digital science notebook for elementary students.
Ph.D., Computer Science (currently enrolled)
North Carolina State University
B.S.E. Electrical/Computer Engineering, B.S. Computer Science (2005)
Publications and Presentations
Robert Sawyer, Andy Smith, Jonathan Rowe, and Roger Azevedo. Enhancing Student Models in Game-Based Learning with Facial Expression Recognition. Proceedings of the Twenty-Fifth Conference on User Modeling, Adaptation, and Personalization, pp. 192-201, Bratislava, Slovakia, 2017.
Robert Sawyer, Andy Smith, Jonathan Rowe, Roger Azevedo, and James Lester. Is More Agency Better? The Impact of Student Agency on Game-Based Learning. Proceedings of the Eighteenth International Conference on Artificial Intelligence in Education, pp. 335-346, Wuhan, China, 2017.
Andy Smith, Osman Aksit, Wookhee Min, Eric Wiebe, Bradford Mott, and James Lester. Integrating Real-Time Drawing and Writing Diagnostic Models: An Evidence-Centered Design Framework for Multimodal Science Assessment. Proceedings of the Thirteenth International Conference on Intelligent Tutoring Systems, pp.165-175, Zagreb, Croatia, 2016.
(Nominated for Best Paper Award)
Angela Shelton, Andy Smith, Eric Wiebe, Courtney Behrle, Ruth Sirkin, and James Lester. Drawing and Writing in Digital Science Notebooks: Sources of Formative Assessment Data. Journal of Science Education and Technology, 23(3), 474-488, 2016.
Andy Smith, Wookhee Min, Bradford Mott, and James Lester. Diagrammatic Student Models: Modeling Student Drawing Performance with Deep Learning. Proceedings of the Twenty-Third Conference on User Modeling, Adaptation, and Personalization, pp. 216-227, Dublin, Ireland, 2015.
Samuel Leeman-Munk, Andy Smith, Bradford Mott, Eric Wiebe, and James Lester. Two Modes are Better Than One: A Multimodal Assessment Framework Integrating Student Writing and Drawing. Proceedings of the Seventeenth International Conference on Artificial Intelligence in Education, pp. 205-214, Madrid, Spain, 2015.
Angi Shelton, Eric Wiebe, Andy Smith, Courtney Behrle. Digital Science Notebooks as a Means for Assessing Student Understanding Through Drawing and Writing. Presented at the National Association for Research in Science Teaching Annual Conference, Chicago, Illinois, 2015.
Andy Smith, Eric Wiebe, Bradford Mott, James Lester. SketchMiner: Mining Learner-Generated Science Drawings with Topological Abstraction. Proceedings of the International Conference on Educational Data Mining, pp. 288-291 London, England, 2014.
Robert Taylor, Andy Smith, Samuel Leeman-Munk, Bradford Mott, and James Lester. Towards ITS Authoring Tools for Domain Experts. Workshop on Intelligent Tutoring System Authoring Tools: Harvesting the Current Crop and Planting Seeds for the Future, Honolulu, Hawaii, 2014.
Andy Smith et al. Investigating Tutor-Student Interactions with a Digital Science Notebook. Presented at the National Association for Research in Science Teaching Annual Conference, Pittsburgh, Pennsylvania, 2014.
Sam Miller, Andy Smith, Sina Bahram, and Robert St Amant. A glove for tapping and discrete 1D/2D input. In Proceedings of the 2012 ACM international conference on Intelligent User Interfaces, pp. 101-104, Lisbon, Portugal 2012.
President’s Volunteer Service Award – Gold Level (2013) – Story – (Radio interview of Chancellor Woodson discussing the award at 1:20)
NCSU College of Engineering Fellowship (2011)
NCSU Graduate Dean’s Fellowship (2010)