MIDAS COVID-19 Special Seminar Series: Wayne Wang, Al Hero, & Walter Dempsey -A scalable tool for longitudinal Twitter analysis: understanding the impact of COVID-19 on public discourse

Wayne Wang*, Al Hero**, & Walter Dempsey***

*PhD Student, Statistics, University of Michigan

**John H. Holland Distinguished University Professor of EECS; R. Jamison and Betty Williams Professor of Engineering, University of Michigan

***Assistant Professor, School of Public Health, University of Michigan

A scalable tool for longitudinal Twitter analysis: understanding the impact of COVID-19 on public discourse

View Recording

Abstract: The open forum of social media provides an opportunity to collect novel data that can by used to study the patterns of social discourse around the COVID-19 pandemic.   We have developed a simple and scalable framework for longitudinal analysis of Twitter data that combines latent topic models (LDA) with computational geometry embeddings to propagate and associate topics over time.   In this talk, we illustrate how the framework can be applied to capture natural progressions of latent topics that are either explicitly or implicitly COVID-related.