A key challenge in STEM education research involves analyzing large amounts of learning process data from classroom interactions, collaborative problem solving in lab settings, and interactions with AI pedagogical agents and other learning technologies. To make informed decisions about curricula, teaching, and personalized instruction, educators working in technologically rich environments need learning analytic models that leverage teachers' qualitative insights as well as the large amounts of data that educational settings now generate, including log files from online learning environments and transcripts of conversations with AI agents. Quantitative ethnography (QE) provides a theoretical framework and set of tools to make sense of the natural language interactions common in traditional STEM learning as well as those occurring in rapidly evolving AI-based platforms. The goal of this Quantitative Ethnography Institute is to increase the capacity of STEM education researchers to use quantitative ethnography to address fundamental questions in STEM education research. QE is a set of statistical, computational, and AI-powered techniques that integrate qualitative and quantitative approaches to understand learning. This QE Institute will recruit three cohorts of 30 participants, the majority of whom will be early-career researchers, to engage in a year-long experience designed to support participants in using QE methods independently and train others to do so. Over the thr