- Faculty: Armando Fox, Marti A. Hearst, John DeNero
- Graduate students: Kristin Stephens-Martinez (PhD), An Ju (MS)
- Undergraduate Students: Krishna Parashar, Regina Ongowarsito, Sreesha Venkat, Nikunj Jain, Maia Rosengarten, Anwar Baroudi, Kavi Gupta, Michelle Tian, Colin Schoen, Kelly Liu, Hannah Huang, Hayden Sheung, Spenser Chiang, and Steven Bi
Large-scale, blended (online/residential) courses are now the norm, especially with the explosion of MOOCs and the huge opportunity for analytics they provide. Our early survey of MOOC instructors  revealed that they valued not only quantitative analytics but also the kind of qualitative information about students that is revealed through (for example) constructed-response assessments. In the context of a large introductory computer science course, we propose a technique  for using each student’s constructed responses in order to identify a subset of their stable conceptual misunderstandings. Our approach is designed for courses with so many students that it is infeasible to interpret every distinct wrong answer manually. Instead, we label only the most frequent wrong answers with the misunderstandings that they indicate, then predict the misunderstandings associated with other wrong answers using statistical co-occurrence patterns. This tiered approach leverages a small amount of human labeling effort to seed an automated procedure that provides new instructor insights into student misunderstandings  with much less effort than inspecting all answers, and generalizes effectively across student cohorts.
- Stephens-Martinez, Kristin, Marti A. Hearst, and Armando Fox. “Monitoring moocs: which information sources do instructors value?.” In Proceedings of the first ACM conference on Learning@ scale conference, pp. 79-88. ACM, 2014.
- Stephens-Martinez, Kristin, An Ju, Colin Schoen, John DeNero, and Armando Fox. “Identifying Student Misunderstandings using Constructed Responses.” In Proceedings of the Third (2016) ACM Conference on Learning@ Scale, pp. 153-156. ACM, 2016.
- Stephens-Martinez, Kristin, An Ju, Krishna Parashar, Regina Ongowarsito, Nikunj Jain, Sreesha Venkat, and Armando Fox. “Taking Advantage of Scale by Analyzing Frequent Constructed-Response, Code Tracing Wrong Answers.” In Proceedings of the 2017 ACM Conference on International Computing Education Research, pp. 56-64. ACM, 2017.