Sarah Hansen
Columbia University, NY·Education Research
Chemistry problems are packed with visual information: chemical symbols, equations, graphs and text. Students who succeed need to know where to look and how to read these pieces.
- Fields
Education Research
Chemistry
Computer Science
- Topics
chemistry education
STEM education
eye tracking
- Grants
- 1 known grant, through Jun 2027
What they work on
- Compare webcam-based eye tracking with traditional screen-based eye tracking while students solve chemistry problems. Determine whether low-cost webcams capture viewing behavior well enough for research and feedback.
- Train and evaluate a machine learning model that uses students' eye-tracking data to predict whether they will solve chemistry problems successfully.
- Test whether early on-screen cues can redirect students' viewing toward relevant parts of a chemistry problem during problem solving. This builds toward a real-time intelligent tutoring system.
More about the research
Struggling students often look in the wrong places, and many never ask for help. This collaborative, multi-university project asks whether eye movements reveal who is on track. If they do, timely hints could steer students toward the parts of a problem that matter.
Why it matters
Many students lose confidence in chemistry, which can push them away from STEM degrees. Automated, personalized feedback based on where students look could help large numbers of learners, including those who do not seek help. Webcam eye tracking could also give chemistry education researchers a cheaper, more accessible tool for studying how students solve problems.
Known grants
From NIH and NSF research grants. Labs often have other funding we can't see.
Closest labs
Maciej Pankiewicz
University of Pennsylvania, PA·Education Research
Extend the Decimal Point mathematics learning game so that a large language model generates hints personalized to each student's problem-solving history, misconceptions and in-game learning behaviors.
Scott Kreher
Dominican University, IL·Education Research
Characterize how beginning students, experienced students and expert faculty understand controlled experiments, using interviews to inform new assessment and teaching tools.
Ryan McMahan
Virginia Polytechnic Institute and State University, VA·Computer Science
Develop and validate the QIS Concept Introductory Test (QISCIT) and label misconceptions in data from a controlled general-population study of QubitVR, a virtual reality app for learning quantum concepts.
The school
Columbia University: 89 labs on PI Pages, $1.4B a year on research, 625 research doctorates a year.
Reach out
A start for your email. Fill in the brackets.