Artificial Intelligence-enabled analysis of social media data to understand public perceptions of COVID-19 contact tracing apps (Preprint)

Kathrin Cresswell, Ahsen Tahir, Zakariya Sheikh, Zain Hussain, Andrés Domínguez Hernández, Ewen Harrison, Robin Williams, Aziz Sheikh, Amir Hussain
2020 Journal of Medical Internet Research  
The emergence of SARS-CoV-2 in late 2019 and its subsequent global spread continues to be a global health crisis. Many governments see contact tracing of citizens through apps installed on mobile phones as a key mechanism to contain the spread of SARS-Cov-2. We here report on an analysis of the suitability of Artificial Intelligence (AI)-enabled social media analysis of Facebook and Twitter to understand public perceptions of COVID-19 contact tracing apps in the United Kingdom. We extracted
more » ... 10,000 relevant social media posts and analysed these, over an eight month period, from 1st of March to 31st of October 2020. We used an initial filter with COVID-19 related keywords, which were pre-defined as part of an open Twitter-based COVID-19 dataset. We then applied a second filter using contract tracing app keywords and a geographical filter. A hybrid rule-based ensemble model was developed and utilised for the study, combining state-of-the-art lexicon rule-based and Deep Learning-based approaches. Overall, we observed 76% positive and 12% negative sentiments, with the majority of negative sentiments being in the North of England. These sentiments varied over time, likely being influenced by ongoing public debates around implementing app-based contact tracing using a centralised model where data would be shared with the health service, versus de-centralised contact-tracing technology. Variations in sentiments corroborate with ongoing debates surrounding the information governance of health related information. AI-enabled social media analysis of public attitudes in healthcare can help to facilitate the implementation of effective public health campaigns.
doi:10.2196/26618 pmid:33939622 pmcid:PMC8130818 fatcat:iuvbut5gfjfitmxel462ue3rvu