Chang is a 5th-year PhD student focusing on the intersection of political science and data science. Her research delves into understanding and analyzing the democratic process in the United States through a multifaceted approach.
By leveraging causal inference, she seeks to identify and establish the relationships between variables that influence democratic outcomes. Through experiments, Chang tests hypotheses about partisan/voter behaviors. Moreover, her work incorporates machine learning methods to analyze large datasets, identifying patterns and making predictions that traditional methods might overlook. She also uses natural language processing (NLP) to analyze textual data, such as public meetings, political speeches, social media content, and legislative documents, to gain insights into public opinion, political discourse, and policy framing.
Overall, Chang's research contributes to a deeper understanding of the mechanisms that drive democratic processes, with potential implications for improving policy-making and fostering more robust democratic institutions in the United States.