How can social media analytics assist authorities in pandemic-related policy decisions? Insights from Australian states and territories

Abstract

Background and objectives: Due to COVID-19, various countries introduced lockdowns and limited citizen movements. These restrictions triggered an increased use of digital technologies and platforms by the public. This provides an opportunity for the authorities to capture public perceptions on COVID-19 from social media channels to make informed decisions. The use of social media analytics during pandemics for decision-making, however, is an understudied area of research. Thus, this study aims to generate insights into how social media analytics can assist authorities in pandemic-related policy decisions.Methods: This study involved a social media analysis approach—i.e., systematic geo-Twitter analysis—that contains descriptive, content, sentiment, and spatial analyses. Australian states and territories are selected as the case study context for the empirical investigation. This study collected 96,666 geotagged tweets (originated from Australia between 1 January and 4 May 2020), and analysed 35,969 of them after data cleaning.Results: The findings disclose that: (a) Social media analytics is an efficient approach to capture the attitudes and perceptions of the public during a pandemic; (b) Crowdsourced social media data can guide interventions and decisions of the authorities during a pandemic, and; (c) Effective use of government social media channels can help the public to follow the introduced measures/restrictions.Conclusion: The findings are invaluable for authorities to understand community perceptions and identify communities in needs and demands in a pandemic situation, where authorities are not in a position to conduct direct and lengthily public consultations.

Pandemic vulnerability knowledge visualisation for strategic decision-making: a COVID-19 index for government response in Australia

“…The primary selection criterion concerned the social media data availability. We obtained geotagged Twitter messages on COVID-19 from Australia ( n = 96,666), via QUT’s Digital Observatory (Yigitcanlar et al , 2020a). Then, a data cleaning process was employed to obtain the mostly relevant tweets for further analysis.…”

Machine Learning Techniques for Sentiment Analysis of COVID-19-Related Twitter Data

“…Sentiment analysis allows investigating people's sentiments and emotions from texts. For example, three studies [76]- [78] solely focused on extracting the users' polarity from COVID-19 datasets with the aim of building more accurate classification models. All three studies used Twitter datasets extracted in 2020, the year of the worldwide outbreak of COVID-19.…”

A new path to address health disparities: How older Aboriginal & Torres Strait Islander women use social media to enhance community health (Protocol)

“…However, only one of the 81 articles reviewed in this scoping review specifically identified Australian users, and Aboriginal and Torres Strait Islander people were not mentioned in this paper. 38 In another scoping review, only five studies examined the impact of social media campaigns on Aboriginal and Torres Strait Islander health. 39 Despite the paucity of studies, Walker et al noted a consistent theme of self-empowerment.…”