Regional sentiments in Covid tweets in the Netherlands before and during peak infections

Tykhonov, Vyacheslav and van Leeuwen, Bas (2021): Regional sentiments in Covid tweets in the Netherlands before and during peak infections.

Abstract

We use numbers of Covid-related tweets over Dutch regions in month 1-9 of 2020. Peaks in tweets precede the peaks of infections by about one month (the exception is June when the corona emergency law (“Spoedwet”) was introduced, which drew a lot of online comments. The reason for this time lag is that more positive sentiments, which resulted in fewer tweets, occurred during peak infections. Just before, more negative sentiments dominated causing more tweets. This positivity in tweets during peak infections has, no doubt, various reasons. Yet, one reason may be in how people value society: the higher the number of infections, the more positive the sentiments related to crucial occupations became, which resulted in fewer tweets. This relation does not hold for non-crucial occupations.

• Item Type: MPRA Paper
• Language: English
• Keywords: Covid, sentiment analysis, Netherlands
• Subjects: A - General Economics and Teaching > A1 - General Economics; D - Microeconomics > D8 - Information, Knowledge, and Uncertainty; J - Labor and Demographic Economics > J4 - Particular Labor Markets

References

The twitter dataset is licensed under the Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International Public License (CC BY-NC-SA 4.0). By using this dataset, you agree to abide by the stipulations in the license, remain in compliance with Twitter’s Terms of Service, and cite the following manuscript: Chen E, Lerman K, Ferrara, E. (2020). “Tracking Social Media Discourse About the COVID-19 Pandemic: Development of a Public Coronavirus Twitter Data Set.” JMIR Public Health Surveill ;6(2):e19273 DOI: 10.2196/19273 PMID: 32427106

Bhat, M., M. Qadri, N. Beg, M. Kundroo, N. Ahanger, and B. Agarwal (2020). “Sentiment analysis of social media response on the Covid19 outbreak.” Brain, behavior, and immunity 87: 136-137. doi:10.1016/j.bbi.2020.05.006

Chakraborty, K., S. Bhatia, S. Bhattacharyya, J. Platos, R. Bag, and A. Hassanien (2020). “Sentiment Analysis of COVID-19 tweets by Deep Learning Classifiers—A study to show how popularity is affecting accuracy in social media.” Applied Soft Computing 97, Part A: 106754.

Daas, P.J.H. (2020). “Ontwikkeling van een Corona sentimentsindicator:Methodologische verantwoording.” CBS. Downloaded from https://www.cbs.nl/nl-nl/over-ons/innovatie/project/corona-sentimentsindicator

Hills, Th., E. Proto, and D. Sgroi (2015). “Historical analysis of national subjective well-being using millions of digitized books,” IZA Discussion Paper No. 9195.

Kruspe, A., M. Haberle, I. Kuhn, and X.X. Zhu (2020). “Cross-language sentiment analysis of European Twitter messages during the COVID-19 pandemic.” ACL Anthology. https://www.aclweb.org/anthology/2020.nlpcovid19-acl.14.pdf

Manguri, K. H., R. N. Ramadhan, and P. R. Mohammed Amin (2020). “Twitter Sentiment Analysis on Worldwide COVID-19 Outbreaks.” Kurdistan Journal of Applied Research 5 (3): 54-65.

Mansoor, M., K. Gurumurthy, R.U. Anantharam, and V. R. Badri Prasad (2020). “Global Sentiment Analysis Of COVID-19 Tweets Over Time.” arXiv:2010.14234v2

OpenStreetMap database is used for geocoding, licensed under the Open Data Commons Open Database License (ODbL) by the OpenStreetMap Foundation (OSMF).

Sloan, L., J. Morgan, W. Housley, M. Williams, A. Edwards, P. Burnap, and O. Rana (2013). “Knowing the tweeters: Deriving sociologically relevant demographics from twitter.” Sociological Research Online 18(3): 7.