Files
Abstract
To address the inefficiencies of the existing manual alumni information collection strategy, this thesis proposes an innovative pipeline to automate alumni information collection and identify the prominent alumni in the three MA programs under The University of Chicago’s Social Science Division (SSD). This thesis utilizes computational methods such as web scrap- ing, text cleaning, and natural language processing to collect and verify alumni data through Google API and Selenium. The preliminary analysis unveils critical revelation of the career trajectories and employment outcomes of SSD alumni. Additionally, this thesis proposes a machine-learning-driven approach for industry classification in mentor matching. As an extension of alumni data collection and management that establishes the groundwork for future integration of SSD’s career service and alumni outreach platforms, a prototype of an all-in-one alumni management and networking web application, SSD Connect, is created. This thesis contributes to the body of literature by providing novel methods and insights for automating alumni information collection, managing and analyzing alumni networks, as well as optimizing alumni management and networking strategies for higher education institutions.