A Presentation by Maria Y. Rodriguez, MSW, PhD
Monday, April 23, 2018
Comparing qualitative and quantitative analysis methods for data exploration, this presentation describes and demonstrates the topic modeling approach for text analysis. Using a sample of tweets with the #WhyIStayed and #WhyILeft hashtags (n = 3,068), a Twitter conversation describing the reasons individuals left or stayed in abusive relationships, a traditional thematic analysis was used to qualitatively code the tweets. The same tweet sample was analyzed using topic models; topics and codes are compared using Linguistic Inquiry and Word Count (LIWC). Results suggest topic modeling offers a data exploration process for qualitative work far less resources intensive than qualitative analysis, particularly for large unstructured data sets.
Dr. Rodriguez is an Assistant Professor at the Silberman School of Social Work, part of the City University of New York’s Hunter College. Her research interests intersect demography, data science, and social policy. Currently, she has three active areas of research: (1) identifying the impacts of the U.S. foreclosure crisis on foreign-born Latinos by examining foreclosure mitigation policy; (2) understanding the impacts of algorithmic decision-making in human services (with particular attention to racially marginalized groups), and (3) using Twitter data and computational social science methods to understand the lived experience of marginalized communities in the United States. She maintains her own blog (https://housingthecity.com) and can be found on Twitter @HousingTheCity.