We have all been in the position of slowly seeing people in the office succumbing to illnesses such as the cold or flu and wondering nervously when the inevitable will happen and we will become affected by the dreaded winter bug. However, scientists have moved beyond the confines of the commercial property workplace and now believe that social network Twitter can help us pinpoint when we will become unwell with startling accuracy.
Researchers used Twitter to track the spread of the flu virus in New York, using a heat map to plot the progression across the city. Using the GPS based “locations” app, which is built into Twitter and can be automatically logged when users check in using a smart phone, they mapped the spread of disease to the point where they could accurately predict which commercial property and residential areas would be hit next.
Adam Sadilek and a team from the University of Rochester analysed the GPS-tagged tweets of over 600,000 users in a single month in 2010. Altogether, this made for 4.4 million Tweets, which were filtered through a special programme to highlight only the relevant ones for research. The programme was coded so as to ignore Tweets complaining about users being “sick” of their commercial property workplace or of a particular activity they were doing at the time, and instead focused only on the word “sick” in the context of illness.
Mr Sadilek explains that the key to predicting the spread of disease is to map user’s social interactions, whether this be through friendships or commercial property work colleagues.
He says; “Given that three of your friends have flu like symptoms, and that you have recently met eight people, possibly strangers, who complained about having runny noses and headaches, what is the probability that you will soon become ill as well?
“Our models enable you to see the spread of infectious diseases, such as flu, throughout a real life population observed through online social media.”
On the plotted heat maps, the “red” zones show particular areas of a town or city that are particularly badly hit, and you can even zoom in for a street by street analysis – an ideal way of figuring out if your commercial property workplace is likely to be affected in the coming days or weeks. In essence, this means that you can predict the likelihood of yourself falling ill when symptoms break out in the vicinity of your home or commercial property workplace. The researchers behind the project claim that the algorithm was correct in 90 per cent of all cases, and could predict illness around eight days in advance.
Mr Sadilek continues; “Our model predicts if and when an individual will fall ill with high accuracy, thereby improving our understanding of the emergence of global epidemics from people’s day-to-day interactions.
“We show emergent aggregate patterns in real time, with second by second resolution.
“By contrast, previous state of the art methods (including Google Flu Trends and government data) entail time lags from days to years.”
This new tool could prove to be incredibly important in the coming years when it is released on to the common market, as institutions such as the NHS could utilise it for predicting particularly busy days for its commercial property hospitals and doctors surgeries over a week in advance, thus giving practises time to prepare staff for a rush of patients.
Additionally, it finally gives us all a legitimate excuse for Tweeting from the office – “Just checking when I’m going to get ill, boss!”
Do you think that social networking has the power to progress from simply a communication tool to a method of improving the health and social responsibility of the general public? Would you think twice about going in to your commercial property place of work if the heat map showed it to be in a “red zone”? Let us know your thoughts in the comments section below.
