Ah, it looks as though we are staring down at the possibility of a Minority Report future – where crimes can be “predicted”, and the perpetrators brought to justice even before anything has been committed, truly bringing new meaning to the adage “prevention is better than cure.” Word has it that researchers at the University of Virginia have shown how tweets on Twitter can be an indicator of select crimes before it happens, assuming the right analysis is applied. In short, what you tweet could prove to be potentially damning evidence against you in the future.
In a research paper that was published in the scientific journal Decision Support Systems in March, analysis of geo-tagged tweets could come in handy when it is used to predict anywhere from 19 to 25 kinds of crimes. Most of the time, such crimes include the likes of stalking, thefts and selected of assault.
The results are nothing short of surprising, especially when you take into consideration that no one in the right mind would want to tweet about their upcoming crimes in a direct manner, at least according to lead researcher Matthew Gerber of the university’s Predictive Technology Lab. Gerber also mentioned that tweets that do not have a direct link to crimes might actually hold information about activities that are more often than not associated with them, sharing, “What people are tweeting about are their routine activities. Those routine activities take them into environments where crime is likely to happen. So if I tweet about getting drunk tonight, and a lot of people are talking about getting drunk, we know there are certain crimes associated with those things that produce crimes. It’s indirect.”
The study saw Gerber and his team analyzing tweets from the city of Chicago that have been tagged to select neighborhoods. These are measured by individual square kilometers as well as the city’s crime database. Will it be used as a tool in fighting crime down the road? Hopefully the algorithm gets it right the first time around though.
Filed in . Read more about Twitter.