Neil Yeung, Jonathan Lai discuss their paper on Data Skeptic podcast
December 14, 2020
Neil Yeung ’23 and Jonathan Lai ’22 recently presented their paper “Face Off: Polarized Public Opinions on Personal Face Mask Usage during the COVID-19 Pandemic” on Data Skeptic, a popular data science podcast reaching more than 30,000 listeners nationwide per week. Hosted by Kyle Polich, the podcast features interviews and discussion of topics related to data science, statistics, machine learning, and artificial intelligence, from the perspective of applying critical thinking and the scientific method to evaluate the veracity of claims and efficacy of approaches.
“Neil and Jonathan did a fantastic job in the interview,” says Jiebo Luo, professor of computer science, who also appeared on the podcast. “I was really impressed by their eloquence and confidence in speaking about their work.” The recording is available online.
The paper, available at https://arxiv.org/abs/2011.00336, uses a novel approach to 1) accurately gauge public sentiment towards face masks in the United States during COVID-19 using a multi-modal demographic inference framework with topic modeling and 2) determine whether face mask policy shifts contributed to polarization around face masks using offline change point analysis on Twitter data.
The paper finds that two key policy-shift events contributed to statistically significant changes in sentiment for both Republicans and Democrats.
- The shift in policy by the CDC on April 3, when it recommended that citizens should wear "non-medical, cloth masks" when it is essential to be in public places, to help prevent the spread of the coronavirus (COVID-19).
- President Donald Trump’s tweet on July 20, 2020 showing himself wearing a face mask and indirectly calling the act "patriotic," a clear pivot away from his earlier reluctance to wear a facial covering in public.
Yeung and Lai also presented the paper at the IEEE International Conference on Big Data, held December 10-13, 2020.