Organization: UC Davis Department of Design
Role: Researcher, Graphic Designer
Year: 2018
As a graduate student in the Department of Design, I began exploring a variety of topics, especially focusing on the intersection of politics and design. In this project, I collected and analyzed the text from each state’s voter I.D. law. The visualization compares law word count to the political party affiliation of the state’s two senators.
Pushing this work further, I partnered with UC Davis’ Data Science Initiative (DSI) to run the laws through Natural Language Processing algorithms. They ran the algorithms and helped me to understand what is interesting amongst the massive files. Two of the algorithms that produced interesting findings were the Term Frequency-Inverse Document Frequency (TF-IDF) and N-gram analysis. The TF-IDF algorithm output showed the word that was most unique to each law in the context of all of the laws combined.
Publicly Presented: November 26, 2018