Bhuwan Dhingra
Duke University, NC·Computer Science
When people search online for answers about vaccines, they often find many questions but few trustworthy answers. The COVID-19 pandemic and the rapid development of vaccines raised a flood of public questions.
- Fields
Computer Science
Public Health & Epidemiology
- Topics
natural language processing
question generation
question answering
- Grants
- 1 known grant, through Aug 2027
What they work on
- Develop automated methods to identify emerging and existing vaccine-related concerns in social media and blogs, and categorize them with a new taxonomy of concerns.
- Generate contextualized questions from online text that capture specific vaccine claims, concerns, knowledge gaps and myths.
- Match generated questions to credible existing answers, or recommend unanswered questions to experts who can write new answers.
- Build a public-facing dashboard, guided by an expert vaccination advisory group, that surfaces ongoing vaccine discussions for public health and medical professionals.
More about the research
These questions keep spreading on social media and blogs, and timely, accurate answers help people make decisions. This project defines "information deficits" as topics where demand for credible information is high but supply is low. It aims to find these gaps automatically, at scale.
Why it matters
Public health officials and medical professionals could use the dashboard to spot growing vaccine concerns and myths early and respond with credible answers. The methods could also support decision-making in other areas where knowledge changes quickly and the public needs reliable answers to hard questions.
Known grants
From NIH and NSF research grants. Labs often have other funding we can't see.
Closest labs
Meng Jiang
University of Notre Dame, IN·Computer Science·Early-career
Develop and compare natural language generation models, one data-driven and one based on theories of abduction, for comparative summarization and argument generation in scientific domains.
Thu Nguyen
University of Maryland, MD·Public Health & Epidemiology
Develop the Rosie chatbot by building a large health information library and improving its natural language processing engine so it reliably understands the many ways new mothers phrase questions.
Kenneth Joseph
University at Buffalo, NY·Computer Science·Early-career
Develop mixed methods combining graph-based and natural-language machine learning with qualitative analysis to identify dominant beliefs about social issues in large datasets from X and Parler.
The school
Duke University: 61 labs on PI Pages, $1.6B a year on research, 417 research doctorates a year.
Reach out
A start for your email. Fill in the brackets.