Although "people don't share with the world that they intend to or have just committed a crime...(but) they do share are things like social events or outings that could lead to criminal activity", said Matthew Gerber, Assistant Professor at the University of Virginia in the US.
For the study, presented at the Joint Statistical Meetings in Baltimore, the team developed statistical crime prediction methods which involved collecting more than 1.5 million public tweets tagged with Chicago-area GPS coordinates spanning January to March of 2013 as well as crime records covering the same period and geographic area.
After dividing and mapping out tweets and crime records onto a grid and identifying common topics of discussion (e.g., sports, restaurants, and entertainment) appearing in tweets, Gerber combined conclusions from this analysis with older forecasting models to predict crimes over the next month.
The result of his combined method was more precise, accurately predicting 19 out of 25 crime types.
"Some cities that utilise such methods as a basis for resource allocation have seen dramatic decreases in crime," Gerber said.
The research could assist police departments in resource allocation, deciding where and when to deploy officers.
(This story has not been edited by Social News XYZ staff and is auto-generated from a syndicated feed.)
Doraiah Chowdary Vundavally is a Software engineer at VTech . He is the news editor of SocialNews.XYZ and Freelance writer-contributes Telugu and English Columns on Films, Politics, and Gossips. He is the primary contributor for South Cinema Section of SocialNews.XYZ. His mission is to help to develop SocialNews.XYZ into a News website that has no bias or judgement towards any.
This website uses cookies.