Social networks could be used to detect epidemics
Sites like Twitter, Facebook could be used to predict weather, disease outbreaks
Social networking sites such as Twitter and Facebook may be able to help researchers detect outbreaks of disease, weather patterns and other phenomena, according to the Press Association.
Social network sites provide snapshots of people's lives on a global basis and Bristol University researchers are looking at whether information gathered from these sties could help predict future events.
Two researchers at the Bristol University Intelligent Systems Laboratory, Professor Nello Cristianini and Vasileios Lampos, conducted the research in Twitter using two case studies, flu outbreaks and rainfall.
In the case of flu, the researchers were able to gather a database over several months of more than 50 million geographically based tweets, which could then be compared with official NHS regional data.
The researchers used state-of-the art technology to discover which keywords in the tweet database were linked with elevated levels of flu and then create a model which transformed keyword instances in tweets into an estimate of the severity of the flu outbreak in that area and predict a possible future epidemic.
"Twitter, in particular, encouraged their 200 million users worldwide to make their posts, commonly known as tweets, publicly available as well as tagged with the user's location. Our research has demonstrated a method, by using the content of Twitter, to track an event, when it occurs and the scale of it. We were able to turn geo-tagged user posts on the microblogging service of Twitter to topic-specific geo-located signals by selecting textual features that showed the content and understanding of the text," Prof Cristianini told the Press Association.