Data-Driven Classroom Interviewing: Data Science to Target Qualitative Research

In this paper, we propose a new method for selecting cases for in situ, immediate interviewresearch: Detector-Driven Classroom Interviewing (DDCI). Published work in educational datamining/learning analytics has yielded highly scalable measures that can detect key aspects ofstudent interaction with computer-based learning in close to real-time. These measures detect avariety of constructs and make it possible to increase the precision and time-efficiency of this formof research. We review four examples that show how the method can be used to study why studentsbecome frustrated and how they respond, how anxiety influences how students respond tofrustration, how meta-cognition interacts with affect, and how to improve the design of an adaptivelearning system. Lastly, we compare DDCI to other mixed-methods approaches and outlineopportunities for data-driven classroom interviewing in research and practice, including researchopportunities, design improvement opportunities, and pedagogical opportunities for teachers.