Equity-Oriented Data Science: Leveraging Computation and Novel Data Sets for Higher Education Research and Practice

Session Type: Symposium

Abstract

Creating equitable systems is a primary goal of higher education researchers and practitioners. However, limited human and financial resources make it challenging to devise timely and targeted ways to improve student experiences, such as helping students navigate course offerings and information. The increasing use of digital technologies for both existing routines and novel practices (e.g., online learning) create much more structured accounts of the ecosystem and enable computational approaches to augment human capacity to support equity and success. This symposium presents four novel studies that address both the evolving nature of equity for students as well as the increasing digitization of higher education by leveraging novel datasets and computational methods.

Sub Unit

• Division D - Measurement and Research Methodologies / Division D - Section 2: Quantitative Methods and Statistical Theory

Chair

• AJ Alvero, Stanford University

Papers

• Measuring Breadth and Depth of Study With Natural Language Processing and Learning Analytics - Annaliese Paulson, University of Michigan - Ann Arbor

• Good Luck With the Blue Book: Computational Approaches to Fairness and Validity in Admissions Testing - Klint Kanopka, Stanford University; Benjamin W. Domingue, Stanford University

• Detecting Diversity, Equity, and Inclusion in Course Syllabi: Applying Topic Modeling for Large-Scale Analysis - Kimberly Williamson, Cornell University

• Understanding Inequalities in Academic Engagement Through Behavioral Analytics - Renzhe Yu, University of California - Irvine

Discussant

• David Lang, Stanford University