Sketch Worksheets in Science, Technology, Engineering, and Mathematics Classrooms: Two Deployments

Abstract

Sketching is a valuable but underutilized tool for science education. Sketch worksheets were developed to help change this, by using artificial intelligence technology to give students immediate feedback and to give instructors assistance in grading. Sketch worksheets use automatically computed visual representations combined with conceptual information to give feedback to students, by computing analogies between students’ sketches and an instructor’s solution sketch. This enables domain experts to develop sketch worksheets, to facilitate dissemination. We describe our experiences in deploying them in geoscience and artificial intelligence classes. The geoscience worksheets, authored by geoscientists at University of Wisconsin–Madison, were used at both Wisconsin and Northwestern University. The artificial intelligence worksheets were developed and used at Northwestern. Our experience indicates that sketch worksheets can provide helpful on-the-spot feedback to students, and significantly improve grading efficiency, to the point where sketching assignments can be more practical to use broadly in science, technology, engineering, and mathematics education.

Deep Learning for Free-Hand Sketch: A Survey

“…Sketch recognition [6] aims to predict the class label of a given sketch, which is one of the most fundamental tasks in computer vision. It has a variety of practical applications including: interactive drawing systems that provide feedback to users [83], sketch-based science education [84], games [5], [54], etc. Both object [5], [6] and scene [85], [86] categories have been studied from a recognition perspective.…”

Using an engagement lens to model active learning in the geosciences

“…The research basis for introducing sketching into undergraduate geoscience courses rests on work done by Mayer (2014) who demonstrated that students learn best when simultaneously interacting with pictures and accompanying textual explanations. Several studies demonstrate the value of sketching for understanding geoscience phenomena (Forbus et al, 2011, Forbus et al, 2018Gobert & Clement, 1999;Jee et al, 2014;Johnson & Reynolds, 2005;Ormand et al, 2017;Reusser et al, 2012;Reynolds & Peacock, 1998;Smith & Bermea, 2012;Steer et al, 2005). With increasing evidence suggesting that sketching and gesturing can increase cognitive engagement and propel active learning in students, Ormand et al (2017)-a research team composed of geoscientists and cognitive psychologists-collaborated to develop two dozen spatial learning activities for mineralogy, structural geology, and sedimentology and stratigraphy courses.…”

“…Additionally, there is need for studies, within and beyond GER, that compare active learning strategies. For example, what are the relative benefits of engaging students in sketching (Forbus et al, 2018) versus classroom response systems (e.g., clickers; LaDue & Shipley, 2018)? What are the impacts on persistence in the geosciences for interventions that build spatial skills (Gold et al, 2018) versus building self-regulation strategies (van der Hoeven Kraft et al, 2014)?…”

Deep Learning for Free-Hand Sketch: A Survey

“…Sketch recognition [1] is to predict the class label for the given sketch, which is one of the most fundamental tasks in free-hand sketch community, with a lot of practical applications, e.g., interactive drawing system that provides some feedback to users [60], sketch-based science education system [61]. Both of object sketches [1], [16] and scene sketches [62], [63] have been studied to date.…”