Social media has revolutionized the way people approach social interactions, expanded people’s world view, and even affected politics. Now, researchers from the Social Data Science Lab at Cardiff University in the UK have found that social media can have a positive impact on policing.
Dr. Peter Burnap, co-author of the study and Reader at Cardiff University’s School of Computer Science and Informatics, said in a statement: “In this research we show that online social media are becoming the go-to place to report observations of everyday occurrences — including social disorder and terrestrial criminal activity.”
Substantial number of people witness crimes every day, and social media gives the common citizen the power to report those crimes in a quick and efficient manner. The 2.8 billion world-wide social media users effectively give police “eyes” everywhere.
The researchers analysed data from the 2011 London riots to conclude that computer systems could scan through Twitter and detect crimes, such as breaking into shops and setting cars on fire, quicker than the Metropolitan Police Service.
The researchers dug up 1.6 million tweets surrounding the 2011 riots. They then used machine-learning algorithms to analyze the tweets. Researchers noted significant details, such as the time and location that the tweets were posted and the content of the tweets. They concluded that the machine algorithms were almost always quicker than the police reports.
The 2011 riots began in Tottenham, but spread quickly. The looting, theft, and destruction that came from the riots were the worst England has seen in over 30 years. When the riots spread to Enfield, reports were slow to reach the police. The researchers note that their system could have gathered this information from Twitter 1 hour and 23 minutes earlier.
This research could equip police officers to better manage and prepare for disruptive events. “It could allow online observations of offline events, enabling better insights into public reports of disruptive events,” explained Burnap. “Ultimately policing services are having to do the same or more in terms of event management, but with less resources. The idea is that this research could augment more traditional approaches to event detection.”
Using social media as a tool to report crimes puts power in the hands of the everyday citizen, so there is often scrutiny surrounding the validity of the social media reports. But, the researchers found a way to filter out false reports.
“The research works at an aggregate level so really only flags events once there is sufficient ‘noise’ around a certain event,” Burnap explained. “This works in two ways – firstly by avoiding identifying individuals in an effort to retain privacy, and also in that it requires effort and collusion to create fake reports as we’re not dependent on taking a single report as evidence of an event.”
Nasser Alsaedi, who has a background in policing and was recently a PhD student under Burnap, pushed forward and completed the research. “Coming from a policing background myself I see the need for this type of cutting edge research every day,” he said in a statement. “I wanted to develop a thesis that could have a real impact in real-world policing. I would like to see this implemented alongside the established decision-making processes.”
The university’s Social Data Science Lab has developed a partnership with the Metropolitan Police Service that is geared towards using social media as a policing tool. The research team is very confident about the future implementation of their work.