There has been little work in exploring students’ behaviors in synchronous digital learning environments. This project fills this gap in the literature by using Natural Language Processing (NLP) to analyze the chat transcripts of educational leadership courses offered in synchronous learning environment. We examine the relationship between chat behaviors, knowledge construction, and student academic achievement outcomes. Findings from the proposed project will help to define learning indicators in such environments, and will also have implications for practitioners, researchers, and designers of online courses.