Menu
Home
Log in / Register
 
Home arrow Computer Science arrow Social Informatics
< Prev   CONTENTS   Next >

4 Discussions and Conclusions

This paper presents an analysis of policing engagement via social media. The aim of our work is to understand what are the characteristics of the content posted by police forces that attracts higher attention levels. By understanding these characteristics we could provide guidelines to the police forces of when and how they should write their posts; so that police messages reach to larger audiences and increase engagement within the communities.

To analyse this content we propose an approach that combines ML techniques with semantic technologies. While ML techniques help us to understand the more discriminative language and time features of those posts generating attention, semantic technologies help us to better understand and categorise the topics emerging from the content. Our analyses show that, writing longer tweets, with positive sentiment, and sending them out before 4pm, was found to increase the probability of attracting attention. Additionally, tweets about weather, roads and infrastructures, mentioning locations are also likely to attract attention.

It is important to highlight that this is a preliminary study and therefore have several limitations. First of all, only one social media platform (Twitter) has been considered for this study. Other social media platforms, such as Facebook, or even news media articles, should be taken into account to have a better understanding of the citizens' engagement towards social media policing content. Secondly, only one police Twitter account has been selected for the analysis performed in this work. Engagement dynamics may vary across the accounts of different police institutions [4]. Finally, only retweets have been considered as engagement indicator. Other indicators, in particular replies, should be also considered.

Additionally to expanding the number of platforms, accounts, and engagement indicators, our future work includes a deeper exploration of how semantics can be used to understand policing content. In particular we aim to explore the relations among tweets via the semantic entities and concepts they share. Our final goal is to be able to analyse conceptual evolution of the posts over time periods.

Acknowledgments. Thanks to all @dorsetpolice for their contribution to this work.

References

1. Rowe, M., Angeletou, S., Alani, H.: Anticipating discussion activity on community forums. In: Third IEEE International Conference on Social Computing (SocialCom 2011), Boston, MA, USA, 9–11 October 2011, pp. 315–322 (2011)

2. Crump, J.: What are the police doing on Twitter? Social media, the police and the public. Policy & Internet 3(4), 1–27 (2011)

3. Sebastian, D., Bayerl, P.S., Kaptein, N.A.: Social media and the police: tweeting practices of british police forces during the August 2011 riots. In: Proceedings of the SIGCHI Conference on Human Factors in Computing Systems. ACM (2013)

4. UK Police Twitter Accounts. https://twitter.com/nickkeane/lists/uk-police-force-twitters

5. NPIA: Engage: Digital and Social Media for the Police Service. National Policing Improvement Agency, London (2010)

6. Earl, J., et al.: This protest will be tweeted: Twitter and protest policing during the Pittsburgh G20. Information, Communication & Society 16(4), 459–478 (2013)

7. Bayerk, P.S., et al:. Who wants police in social media. In: Proceedings of the European Conference of Social Media, Brighton, UK (2014)

8. Cha, M., Haddadi, H., Benevenuto, F., Gummadi, K.P.: Measuring user influence in twitter: The million follower fallacy. In: Proc. 4th Int. AAAI Conf. on Weblogs and Social Media (ICWSM), Washington, DC (2010)

9. Gomez, V., Kaltenbrunner, A., López, V.: Statistical analysis of the social network and discussion threads in slashdot. In: WWW 2008: Proceeding of the 17th International Conference on World Wide Web, pp. 645–654. ACM, New York (2008)

10. Naveed, N., Gottron, T., Kunegis, J., Alhadi, A.C.: Bad news travel fast: A content-based analysis of interestingness on twitter. In: Proc. 3rd Int. Conf. on Web Science, 2011, Bon, Germany (2011)

11. Sousa, D., Sarmento, L., Rodrigues, E.M.: Characterization of the twitter @replies network: are user ties social or topical? In: Proceedings of the 2nd International Workshop on Search and Mining User-generated Contents (SMUC), Toronto, Canada (2010)

12. Suh, B., Hong, L., Pirolli, P., Ed Chi, H.: Want to be retweeted? Large scale analytics on factors impacting retweet in Twitter network. In: Proc. IEEE Second Int. Conf. on Social Computing (SocialCom) (2010)

 
Found a mistake? Please highlight the word and press Shift + Enter  
< Prev   CONTENTS   Next >
 
Subjects
Accounting
Business & Finance
Communication
Computer Science
Economics
Education
Engineering
Environment
Geography
Health
History
Language & Literature
Law
Management
Marketing
Philosophy
Political science
Psychology
Religion
Sociology
Travel