Studying Educational Inequality with Big Data and Computational Methods

A growing amount of educational data are available online, and those that are not yet online can be digitalized and analyzed at an unprecedented speed. During the pandemic, a lot of teaching and learning had gone remote, which makes the types of online data and their implications for educational inequality even more relevant to the study of social stratification. This session invites research on curricula, textbooks, course-taking trajectories, and other similar types of educational big data available today. The session highlights methods such as natural language processing, network analysis, machine learning, and other computational social science methods broadly defined when analyzing these data. With a growing number of researchers around the world actively working on the related data and methodologies, this session seeks to stimulate conversations among them and shed light on the future direction of this research area.