Conference proceeding
Adaptive Support for Representation Skills in a Chemistry ITS Is More Effective Than Static Support
ARTIFICIAL INTELLIGENCE IN EDUCATION (AIED 2019), PT I, Vol.11625, pp.432-444
Lecture Notes in Artificial Intelligence
01/01/2019
DOI: 10.1007/978-3-030-23204-7_36
Abstract
Multiple visual representations can enhance learning in STEM, provided that students have prerequisite representation skills to make sense of how the visuals show information and to fluently perceive meaning in the visuals. Prior research shows that instructional support for sense-making skills and perceptual fluency enhances STEM learning. This research also shows that students need different types of support, depending on their prior representation skills. Hence, instruction may be most effective if it adaptively assigns students to support for sense-making skills and perceptual fluency. We tested this hypothesis in an experiment with 45 undergraduates in an introductory chemistry course. Students were randomly assigned to a 6-week instructional module of an intelligent tutoring system (ITS) that (1) provided a static sequence of activities that supported sense-making skills and perceptual fluency or (2) adaptively assigned the activities. Results show that the adaptive version yielded significantly higher gains of chemistry knowledge. Our findings expand theories of representation skills and yield recommendations for ITS s with multiple visual representations.
Details
- Title: Subtitle
- Adaptive Support for Representation Skills in a Chemistry ITS Is More Effective Than Static Support
- Creators
- Martina A. Rau - University of Wisconsin–MadisonMiranda Zahn - University of Wisconsin–MadisonEdward Misback - University of Wisconsin–MadisonJudith Burstyn - University of Wisconsin–Madison
- Contributors
- S Isotani (Editor)E Millan (Editor)A Ogan (Editor)P Hastings (Editor)B McLaren (Editor)R Luckin (Editor)
- Resource Type
- Conference proceeding
- Publication Details
- ARTIFICIAL INTELLIGENCE IN EDUCATION (AIED 2019), PT I, Vol.11625, pp.432-444
- Publisher
- Springer Nature
- Series
- Lecture Notes in Artificial Intelligence
- DOI
- 10.1007/978-3-030-23204-7_36
- ISSN
- 0302-9743
- eISSN
- 1611-3349
- Number of pages
- 13
- Grant note
- DUE-IUSE 1611782 / NSF; National Science Foundation (NSF)
- Language
- English
- Date published
- 01/01/2019
- Academic Unit
- Psychological and Quantitative Foundations
- Record Identifier
- 9984701735402771
Metrics
1 Record Views