Social media to be used to detect outbreak of diseases
TWITTER and Facebook could be used to help detect outbreaks of disease and other phenomena, academics said today.
The social network sites provide snapshots of people's lives and researchers at Bristol University have examined whether the power of Twitter and Facebook can be harnessed to predict future events.
Professor Nello Cristianini and Vasileios Lampos at the university's Intelligent Systems Laboratory conducted the research on Twitter using two case studies - rainfall and the outbreak of flu.
In the case of flu, over several months the researchers were able to gather a database of more than 50 million geographically based tweets, which could then be compared with official NHS regional data.
The researchers deployed state-of-the art technology to figure out which keywords in the database of tweets were associated with elevated levels of flu.
In this way they were able to create a predictive model that transformed keyword incidence in tweets into an estimate of the severity of flu in that area and predict whether an epidemic was emerging.
Prof Cristianini said: "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.
"This has led to a new wave of experimentation and research using an independent stream of information.
"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 said that while Twitter users do not represent the general population the study indicated that microblogging sites could be used to track an event.
Future work could be focused on improving various subtasks in the methodology, enabling researchers to become ever more expert at pinpointing situations, such as a electoral voting intentions.