Tuesday 12pm, 3 October 2017


Dissertation Talk: Serving CS Formative Assessment Guidance using Simple and Practical Instructor-Bootstrapped Error Models

Kristin Stephens-Martinez

PhD Student - UC Berkeley


Classes are growing in size and adding more and more technology. These two factors are scaling classes and requiring us to reconsider teaching practices that originated in small classes with little technology. However, rather than seeing this as a problem, I believe scale can help classes. This scale is an opportunity to collect and analyze large, high-dimensional data sets, and a way that enables us to conduct experiments at scale. In this talk, I show one way to investigate how scale can help the classroom. I will start with results from surveying MOOC instructors on what information sources they valued. Next, I discuss analyzing a large data set of constructed-response, code-tracing wrong answers using mixed methods of quantitative and qualitative techniques. And then, I present my deployment of a scaled hint intervention using the insights from the analysis. Finally, I will close with lessons I learned while investigating how scale can help the classroom.


Kristin Stephens-Martinez is a Ph.D. candidate here at UC Berkeley, advised by Armando Fox in Computer Science Education. She is a founding member of ACE Lab, Algorithms and Computing for Education (, and the founder of EECS Peers (, a graduate student group dedicated to supporting fellow grad students with grad school life. Her research interests focus on using data to find insights that can be turned into learning interventions. Kristin has served as a teaching assistant for upper and lower division classes with enrollments up to 1,000's of students and co-taught an undergraduate seminar on education technology. In addition, she has mentored thirteen undergraduates in research, mentored ten graduate students through the WICSE Little/Big Sisters program and EECS Peers, and served as a discipline cluster leader at the UC Berkeley Conference for First-Time GSIs.