Using Natural Language Processing and Crowdsourcing to Monitor and Evaluate Public Information and Communication Disparities about Colon Cancer Screening
Efforts to improve public health communication about colorectal cancer (CRC) and CRC screening (CRCS) require understanding what information is commonly seen by target audiences and consideration of existing information and behavior disparities for populations at higher risk for CRC (e.g., Black Americans). This project uses novel computational approaches to monitor the public communication environment about CRCS, crowdsourcing to engage in formative evaluation of possible message content, and a randomized, controlled trial to validate these computational and crowdsourcing approaches. The Computational Communication Lab is leading the first phase of this effort, using computational, natural language processing approaches to capture and analyze digital and social media information about CRC and CRCS to identify prominent messages, sources and types of misinformation, and information inequalities.
Funded by the National Institute of Health, Award #R37CA259156
Deterring objectionable behavior and fostering emergent norms in social media conversations
This work seeks to develop a theoretical model for understanding the emergence and maintenance of norms to deter objectionable behavior through a multi-level, multi-method inquiry. We will test the impact of different ways of objecting to misinformation, hate speech, and harassment under different collective conditions in the audience and the social media platform. Specifically we ask: if an individual objects to an “offense” in this way under these conditions, how will this objection influence future behavior in the community? In particular, will it encourage or discourage a norm suppressing such offensive speech? The project proceeds in four research phases: real world observation, individual-level experimentation, agent-based simulation, and collective-level experimentation as well as a field implementation phase.
Funded by National Science Foundation Award # IIS-2106476