Statistically Evaluating Social Media Sentiment Trends towards COVID-19 Non-Pharmaceutical Interventions with Event Studies

Jingcheng Niu, Erin E. Rees, Victoria Ng and Gerald Penn.
SMM4H 2021 @ NAACL

ACL Anthology

TL;DR

Event studies — the financial-sector method for attributing stock-price fluctuations to announcements — can rigorously attribute social-media sentiment changes to policy-level COVID-19 non-pharmaceutical interventions (NPIs), bringing proper event attribution and significance testing to a literature that lacked both. A case study of Twitter sentiment towards policy-level NPIs in Canada confirms a generally positive connection between NPI announcements and sentiment, with a promising correlation to a public-health survey of popular compliance.

How to Cite

@inproceedings{niu-etal-2021-statistically,
   title = "Statistically Evaluating Social Media Sentiment Trends towards {COVID}-19 Non-Pharmaceutical Interventions with Event Studies",
   author = "Niu, Jingcheng and
    Rees, Erin and
    Ng, Victoria and
    Penn, Gerald",
   booktitle = "Proceedings of the Sixth Social Media Mining for Health ({\#}SMM4H) Workshop and Shared Task",
   month = jun,
   year = "2021",
   address = "Mexico City, Mexico",
   publisher = "Association for Computational Linguistics"
}