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

Policing Engagement via Social Media

Abstract. Social Media is commonly used by policing organisations to spread the word on crime, weather, missing person, etc. In this work we aim to understand what attracts citizens to engage with social media policing content. To study these engagement dynamics we propose a combination of machine learning and semantic analysis techniques. Our initial research, performed over 3,200 posts from @dorsetpolice Twitter account, shows that writing longer posts, with positive sentiment, and sending them out before 4pm, was found to increase the probability of attracting attention. Additionally, posts about weather, roads and infrastructures, mentioning places, are also more likely to attract attention.

Keywords: Social web • Semantic web • Engagement • Police

1 Introduction

Social media is now commonly used to help communicate policing messages to the general public. Many forces have staff dedicated to this purpose and to improve the spreading of key messages to wider social media communities. However, while guidance reports claim that social media can enhance the reputation and accessibility of police staff to their communities [5], research studies have shown that exchanges between the citizens and the police are infrequent. Social media works as an extra channel for delivering messages but not as a mean for enabling a deeper engagement with the public. [2]

Studies targeting citizen engagement towards police forces in social media have been mainly focused on studying the different social media strategies that police forces use to interact with the public [2, 3, 5, 6]. However, it is still unclear which factors drive the attention of citizens towards social media messages coming from police information sources. There are various parameters that can influence engagement on Twitter, such as the characteristics of the content, writing style, time of posting, network position, etc. [1, 8, 9, 10, 11, 12]. Analysing these parameters can help identifying actions and recommendations that could increase public's engagement.

In this paper we present a pilot study developed in collaboration with the Dorset Police, UK. This organisation is moving towards a more engaging style of social media usage and it is interested in scientifically identifying best practices for engaging the public on Twitter. For the purpose of this study we have collected 3,200 posts from @dorsetpolice Twitter account and we have investigated the key characteristics of those messages attracting the citizen's attention. To investigate engagement towards these messages we propose a combination of Machine Learning (ML) and semantic analysis techniques. Using ML analysis techniques we aim to identify the key language and time features of those messages. In addition, a semantic content analysis is used to investigate the key topics (concepts and entities) associated with engagement.

Our results show that writing longer tweets, with positive sentiment, and sending them out before 4pm, was found to increase the probability of attracting attention. Additionally, citizens are more interested about tweets mentioning places and related with topics such as weather conditions, roads and infrastructures. Note that, this study is not meant to be a representative of all forces, but rather a focused study on

@dorsetpolice. Future work will include the analysis of other police forces [4].

The rest of the paper is organised as follows. Section 2 provides an overview of the related work in the area of policing engagement in social media. Section 3 describes the dataset used in this work and the results of the conducted engagement analyses. Conclusions are reported in section 4.

 
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