As the COVID-19 pandemic sweeps across the globe, police forces are charged with new roles as they engage and enforce new policies and laws governing societal behaviours. However, how the police exercise these powers is an important factor in shaping public opinion and confidence concerning their activities across space and time. This research developed an analytical framework for measuring the inequality in the public opinion towards policing efforts during the pandemic using Twitter data. We demonstrate the utility of our framework using 3-months of tweets across 42 police force areas (Pfas) of England and Wales (UK). The results reveal that public opinions on policing is overwhelmingly negative across space and time, and that these opinions have been most exacerbated by the COVID-19 pandemic in three specific Pfas, namely Staffordshire, Thames Valley, and North Wales. We provided the link to the open-source script by which this research could be replicated and adapted to other study areas. This research has the potential to help law enforcement understand the dynamics of public confidence and trust in policing and facilitate action towards improved police services.
References
[1]
Langan, P., Greenfeld, L., Smith, S., Durose, M. and Levin, D. (2001) Contacts Between Police and the Public: Findings from the 1999 National Survey. Bureau of Justice Statistics, Washington DC.
[2]
Mastrofski, S. (1981) Surveying Clients to Assess Police Performance: Focusing on the Police-Citizen Encounter. Evaluation Review, 5, 397-408.
https://doi.org/10.1177%2F0193841X8100500308
[3]
Mestre, J. (1992) Community Feedback Program: Twelve Years Later. Law and Order, 40, 57-60.
[4]
Liu, B. (2012) Sentiment Analysis and Opinion Mining. Synthesis Lectures on Human Language Technologies, 5, 1-167.
https://doi.org/10.2200/S00416ED1V01Y201204HLT016
[5]
Balahur, A., Mihalcea, R. and Montoyo, A. (2014) Computational Approaches to Subjectivity and Sentiment Analysis: Present and Envisaged Methods and Applications. Computer Speech & Language, 28, 1-6.
https://doi.org/10.1016/j.csl.2013.09.003
[6]
Liu, B. (2015) Sentiment Analysis: Mining Opinions, Sentiments, and Emotions. Cambridge University Press, Cambridge.
https://doi.org/10.1017/CBO9781139084789
[7]
Istia, S. and Purnomo, H. (2018) Sentiment Analysis of Law Enforcement Performance Using Support Vector Machine and K-Nearest Neighbor. 3rd International Conference on Information Technology, Information System and Electrical Engineering, Yogyakarta, 13-14 November 2018, 84-89.
https://doi.org/10.1109/ICITISEE.2018.8720969
[8]
Hand, L.C. and Ching, B.D. (2019) Maintaining Neutrality: A Sentiment Analysis of Police Agency Facebook Pages before and after a Fatal Officer-Involved Shooting of a Citizen. Government Information Quarterly, 37, Article ID: 101420.
https://doi.org/10.1016/j.giq.2019.101420
[9]
Laufs, J. and Waseem, Z. (2020) Policing in Pandemics: A Systematic Review and Best Practices for Police Response to COVID-19. International Journal of Disaster Risk Reduction, 51, Article ID: 101812. https://doi.org/10.1016/j.ijdrr.2020.101812
[10]
Chukwusa, E., Johnson, H. and Gao, W. (2020) An Exploratory Analysis of Public Opinion and Sentiments towards COVID-19 Pandemic Using Twitter Data. Research Square. https://doi.org/10.21203/rs.3.rs-33616/v1
[11]
Xue, J., Chen, J., Chen, C., Hu, R. and Zhu, T. (2020) The Hidden Pandemic of Family Violence during COVID-19: Unsupervised Learning of Tweets. Journal of Medical Internet Research, 22, e24361. https://doi.org/10.2196/24361
[12]
Jiang, Y. Li, Z. and Ye, X. (2019) Understanding Demographic and Socioeconomic Biases of Geotagged Twitter Users at the County Level. Cartography and Geographic Information Science, 46, 228-242.
https://doi.org/10.1080/15230406.2018.1434834
[13]
Paul, D., Li, F., Teja, M., Yu, X. and Frost, R. (2017) Compass: Spatio Temporal Sentiment Analysis of US Election What Twitter Says! Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Halifax, August 2017, 1585-1594. https://doi.org/10.1145/3097983.3098053
[14]
Malik, M., Lamba, H., Nakos, C. and Pfeffer, J. (2015) Population Bias in Geotagged Tweets. Proceedings of the 2015 International AAAI Conference on Web and Social Media, Oxford, 26-29 May 2015, 18-27.
[15]
Pavalanathan, U. and Eisenstein, J. (2015) Confounds and Consequences in Geotagged Twitter Data. 2015 Conference on Empirical Methods in Natural Language Processing, September 2015, 2138-2148. https://doi.org/10.18653/v1/D15-1256
[16]
Kelman, H.C. (1961) Processes of Opinion Change. Public Opinion Quarterly, 25, 57-78. https://doi.org/10.1086/266996
[17]
Kucher, K., Paradis, C. and Kerren, A. (2018) The State of the Art in Sentiment Visualization. Computer Graphics Forum, 37, 71-96.
https://doi.org/10.1111/cgf.13217
[18]
Chakraborty, K., Bhatia, S., Bhattacharyya, S., Platos, J., Bag, R. and Hassanien, A. E. (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, Article ID: 106754. https://doi.org/10.1016/j.asoc.2020.106754
[19]
Xue, J., Chen, J., Chen, C., Zheng, C., Li, S. and Zhu, T. (2020) Public Discourse and Sentiment during the COVID 19 Pandemic: Using Latent Dirichlet Allocation for Topic Modeling on Twitter. PLoS ONE, 15, e0239441.
https://doi.org/10.1371/journal.pone.0239441
[20]
Samuel, J., Ali, G.G.M.N., Rahman, M.M., Esawi, E. and Samuel, Y. (2020) COVID-19 Public Sentiment Insights and Machine Learning for Tweets Classification. Information, 11, 314. https://doi.org/10.31234/osf.io/sw2dn
[21]
Nikolovska, M., Johnson, S. and Ekblom, P. (2020) “Show This Thread”: Policing, Disruption and Mobilisation through Twitter. An Analysis of UK Law Enforcement Tweeting Practices during the Covid-19 Pandemic. Crime Science, 9, Article No. 20.
https://doi.org/10.1186/s40163-020-00129-2
[22]
Heverin, T. and Zach, L. (2010) Twitter for City Police Department Information Sharing. Proceedings of the American Society for Information Science and Technology, 47, 1-7. https://doi.org/10.1002/meet.14504701277
[23]
Crump, J. (2011) What Are the Police Doing on Twitter? Social Media, the Police and the Public. Policy & Internet, 3, 1-27. https://doi.org/10.2202/1944-2866.1130
[24]
Lieberman, J.D., Koetzle, D. and Sakiyama, M. (2013) Police Departments’ Use of Facebook: Patterns and Policy Issues. Police Quarterly, 16, 438-462.
https://doi.org/10.1177/1098611113495049
[25]
Kearney, M.W. (2019) Rtweet: Collecting and Analyzing Twitter Data. Journal of Open Source Software, 4, Article No. 1829. https://doi.org/10.21105/joss.01829
[26]
Office of National Statistics (2015) Major Towns and Cities (December 2015) Names and Codes in England and Wales. Office of National Statistics, London.
[27]
Silge, J. and Robinson, D. (2016) Tidytext: Text Mining and Analysis Using Tidy Data Principles in R. Journal of Open Source Software, 1, Article No. 37.
https://doi.org/10.21105/joss.00037
[28]
Nielsen, F. (2011) A New ANEW: Evaluation of a Word List for Sentiment Analysis in Microblogs. 8th Extended Semantic Web Conference, Heraklion, 29 May-2 June 2011, 93-98.
[29]
Hu, M. and Liu, B. (2004) Mining and Summarizing Customer Reviews. Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, Seattle, August 2004, 168-177.
https://doi.org/10.1145/1014052.1014073
[30]
Malshe, A. (2019) Data Analytics Applications.
https://ashgreat.github.io/analyticsAppBook/index.html
[31]
Fisher, R.A. (1935) The Design of Experiments. Hafner, New York.
[32]
Good, P. (2006) Resampling Methods. 3rd Edition, Birkhauser, Basel.
[33]
Adepeju, M. (2021) Opitools: A Tool for Analyzing Opinions in a Text Document.
https://cran.r-project.org/web/packages/opitools/index.html
[34]
Walsh, J.P. (2019) Social Media and Border Security: Twitter Use by Migration Policing Agencies. Policing and Society, 30, 1138-1156.
https://doi.org/10.1080/10439463.2019.1666846
