Date of Degree
Data Analysis & Visualization
NLP, Stance Detection, Covid-19 vaccine
The growing polarization in the United States has been widely reported. Media coverage plays an important role in shaping public opinion and influences public debates on complex and unfamiliar topics. There are some benefits to individuals and society from political polarization and conflict between opposing viewpoints. However, recent research has primarily highlighted the negative consequences of polarization which reached an all-time high. One such topic is the Covid-19 vaccine which was developed in record time, and the public learned about its safety and possible risks through the media coverage.
In this capstone, we examine U.S. news media coverage on the Covid-19 vaccine topic as an illustration of a debate in a polarized environment through the stance in the media on vaccine safety. Specifically, we analyze opinion-framing in the Covid-19 vaccine debate as a way of attributing a statement or belief to someone else. We focus on self-affirming and opponent-doubting discourse and analyze if Left-leaning and Right-leaning media engage in self-affirming or opponent-doubting discourse. For example, a health expert would say that “The leading researchers agree that Covid-19 vaccines are safe and effective,” while a vaccine skeptic would say that “Mistaken researchers claim that Covid-19 vaccines are safe and effective”.
We introduce VacStance, a dataset of 2,000 stance-labeled Covid-19 vaccine sentences extracted from 169,432 sentences drawing from 15,750 news articles covering left-leaning and right-leaning media outlets. We run a trained BERT classifier to analyze aspects of argumentation, how the different sides of the vaccine debate represent their own and each other’s opinions. To the best of our knowledge, VacStance is the first data set of media Covid-19 vaccine stances. Our data set and model is made available in GitHub for future projects on Covid-19 vaccine opinion-framing and stance detection.
Ceslov, Rodica, "Detecting Stance on Covid-19 Vaccine in a Polarized Media" (2021). CUNY Academic Works.