Measuring Shifts in Attitudes Towards COVID-19 Measures in Belgium Using Multilingual BERT

TL;DR

This study uses multilingual BERT to analyze Belgian COVID-19 tweets over seven months, tracking shifts in public opinion and discussion topics in relation to government measures and events.

Contribution

It introduces a multilingual BERT-based approach to classify and analyze public sentiment and topic shifts on social media during the pandemic in Belgium.

Findings

Public opinion on measures changed over time.

Discussion topics evolved with pandemic developments.

Sentiment analysis correlated with policy changes.

Abstract

We classify seven months' worth of Belgian COVID-related Tweets using multilingual BERT and relate them to their governments' COVID measures. We classify Tweets by their stated opinion on Belgian government curfew measures (too strict, ok, too loose). We examine the change in topics discussed and views expressed over time and in reference to dates of related events such as implementation of new measures or COVID-19 related announcements in the media.