Inferring COVID-19 Vaccine Attitudes from Twitter Data : An Application to the Arabic Speaking World

This study investigates whether Twitter data can be used to infer attitudes towards COVID-19 vaccination with an application to the Arabic speaking world. At first glance, anti-vaccine sentiment estimated from Twitter data is surprisingly low in comparison to estimates obtained from survey data. Only about 3 percent of Twitter accounts in our database are identified as anti-COVID-vaccination (compared to 20 to 30 percent of survey respondents). This bias is resolved when: (1) filtering out accounts belonging to organizations that make up a significant share of the discourse on Twitter, and (2) adjusting for the fact that the population of Twitter users is biased towards more educated individuals. The most effective messages on the anti-vaccine side highlight claims that the vaccine causes serious life-threatening side effects. In the pro-vaccine camp, tweets containing content showing public figures receiving the vaccine are found to have the largest reach by far.

Saved in:
Bibliographic Details
Main Author: Van Der Weide, Roy
Format: Working Paper biblioteca
Language:English
English
Published: World Bank, Washington, DC 2022-09
Subjects:VACCINE SENTIMENT, ARABIC TWITTER SENTIMENT DATA, ANTI-VACCINE SOCIAL MEDIA, COVID VACCINE SIDE EFFECT ATTITUDES, SOCIAL MEDIA VACCINE ENDORSEMENTS, POSITIVE VACCINE MESSAGING, COVID-19 PANDEMIC, HEALTH BEHAVIOR, PUBLIC HEALTH PROMOTION, PUBLIC HEALTH SURVEY VS TWITTER DATA,
Online Access:http://documents.worldbank.org/curated/en/099545109062215988/IDU09209a2550575104cbf0b5dc0990c0568bc5a
http://hdl.handle.net/10986/37970
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This study investigates whether Twitter data can be used to infer attitudes towards COVID-19 vaccination with an application to the Arabic speaking world. At first glance, anti-vaccine sentiment estimated from Twitter data is surprisingly low in comparison to estimates obtained from survey data. Only about 3 percent of Twitter accounts in our database are identified as anti-COVID-vaccination (compared to 20 to 30 percent of survey respondents). This bias is resolved when: (1) filtering out accounts belonging to organizations that make up a significant share of the discourse on Twitter, and (2) adjusting for the fact that the population of Twitter users is biased towards more educated individuals. The most effective messages on the anti-vaccine side highlight claims that the vaccine causes serious life-threatening side effects. In the pro-vaccine camp, tweets containing content showing public figures receiving the vaccine are found to have the largest reach by far.