Accepted for/Published in: Journal of Medical Internet Research
Date Submitted: Jun 15, 2022
Date Accepted: Aug 10, 2022
Date Submitted to PubMed: Sep 23, 2022
A comparative geolocation and text mining analysis of emotions and topics during the COVID-19 Pandemic in the UK
ABSTRACT
Background:
In recent years, the COVID-19 pandemic has brought great changes to public health, society and the economy. Social media provides a platform for people to discuss health concerns, living conditions and policies during the epidemic, which allows policy makers to use its contents to analyse the public emotions and attitudes for decision making.
Objective:
In this study, we used deep learning-based methods to understand public emotions on topics related with the COVID-19 pandemic in the UK through a comparative geolocation and text mining analysis on Twitter.
Methods:
Over 500,000 tweets related to COVID-19 from 48 different cities in the UK were extracted, and the data cover the period of the last 2 years (from January 2020 to December 2021). We leveraged three advanced deep learning-based models: SenticNet 6 for sentiment analysis, SpanEmo for emotion recognition, and Combined Topic Modelling (CTM) for topic modelling to geospatially analyse the emotions and topics of tweets in the UK.
Results:
According to the analysis, we observed a significant change in the number of tweets as the epidemiological situation and vaccination these two years. Our findings reveal people’s attitudes and emotions towards topics related to COVID-19. For sentiment, about 60% of tweets are positive, 20% neutral and 20% are negative. For emotion, optimism and anticipation are the most frequently expressed emotions, while trust is the lowest expressed emotion. In addition, the proportion of emojis, sentiments, emotions and topics varies from city to city.
Conclusions:
Through large scale text mining of Twitter, our study found that there were meaningful differences in public emotions and topics regarding the COVID-19 pandemic among different UK cities. Furthermore, efficient comparative analysis can be used to track people’s thoughts, feelings and needs. Therefore, our approach of exploring public emotions and topics from Twitter can potentially lead to informing how public policies can be adapted to a particular geographical area.
Citation
Request queued. Please wait while the file is being generated. It may take some time.
Copyright
© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.