Faculty Spotlight

Advanced Topic Modeling Methods to Analyze Text Responses in COVID-19 Survey Data
Philip Resnik (Principal Investigator)

As the COVID-19 pandemic continues, public and private organizations are deploying surveys to inform responses and policy choices. Survey designs using multiple choice responses are by far the most common -- "open ended" questions, where survey participants provide a longer-form written response, are used far less. This is true despite the fact that when you allow people to provide unconstrained spoken or text responses, it is possible to obtain richer, fine-grained information clarifying the other responses, as well as useful "bottom up" information that the survey designers did not know to ask for. A key problem is that analyzing the unstructured language in open-ended responses is a labor-intensive process, creating obstacles to using them especially when speedy analysis is needed and resources are limited. Computational methods can help, but they often fail to provide coherent, interpretable categories, or they can fail to do a good job connecting the text in the survey with the closed-end responses. This project will develop new computational methods for fast and effective analysis of survey data that includes text responses, and it will apply these methods to support organizations doing high-impact survey work related to COVID-19 response. This will improve these organizations' ability to understand and mitigate the impact of the COVID-19 pandemic.

This project's technical approach builds on recent techniques bringing together deep learning and Bayesian topic models. Several key technical innovations will be introduced that are specifically geared toward improving the quality of information available in surveys that include both closed- and open-ended responses. A common element in these approaches is the extension of methods commonly used in supervised learning settings, such as task-based fine-tuning of embeddings and knowledge distillation, to unsupervised topic modeling, with a specific focus on producing diverse, human-interpretable topic categories that are well aligned with discrete attributes such as demographic characteristics, closed-end responses, and experimental condition. Project activities include assisting in the analysis of organizations' survey data, conducting independent surveys aligned with their needs to obtain additional relevant data, and the public release of a clean, easy to use computational toolkit facilitating more widespread adoption of these new methods.

Click here to read previous ARHU Faculty Spotlights.

The National Endowment for the Humanities (NEH) has awarded a $50,000 collaborative research grant to the College of Arts and Humanities’ Center for Global Migration Studies for a project entitled “Immigration and the Making of African America.” Led by Julie Greene, professor of history, the project will explore the largely untold history of immigrants from Africa, the Caribbean and Latin America and how they have influenced African American culture and society during the 20th and 21st centuries. 

The grant will support a conference in April 2020 that will connect humanities scholars across the nation as well as fund the planning of a future publication. Scholars will also engage with curators from the Smithsonian Institute’s National Museum of African American History and Culture. 

“Across the 20th century, and particularly since 1965, immigration from across the African diaspora has profoundly reshaped the African American experience,” said Greene. “Yet only rarely do immigration scholars and African Americanists engage in dialogue with one another. This project aims to bridge that gap, and along the way, illuminate experiences of race and migration in the modern United States.” 

Greene is director of the Center for Global Migration Studies at the University of Maryland. Her particular interests are in the history of labor and immigration. Her most recent book, “The Canal Builders: Making America's Empire at the Panama Canal,” focuses on the tens of thousands of working men and women who traveled across the world to live and labor on the canal project. 

The National Endowment for the Humanities is an independent federal agency that supports research and learning in history, literature, philosophy and other areas of the humanities. Created in 1965, the agency reviews and funds selected proposals from around the country.  The highly competitive Collaborative Research Grant is awarded to approximately 14 percent of all submitted proposals.

For more information on Greene’s NEH grant and others awarded during this grant cycle, visit the NEH website.