Research suggests that social media could track flu outbreaks
Share
Social media could be used to track an event or phenomena such as flu outbreaks or rainfall rates, according to new research.
A team from Bristol University’s Intelligent Systems Laboratory built a predictive model that was able to identify key words in messages posted to the website Twitter associated with elevated levels of flu and estimate the severity of the disease in a specific area.
Although Twitter does not represent the general population, the researchers said the study suggests the website could be used to track such an event.
Professor Nello Cristianini, who carried out the research, said Twitter’s 200-million users worldwide were encouraged to include a geo-location information ‘tag’ with their messages, which has encouraged a new wave of experimentation and research.
‘Our research has demonstrated a method, by using the content of Twitter, to track an event when it occurs and the scale of it,’ she said.
‘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.’
Over several months, the researchers were able to gather a database of more than 50-million geo-located tweets, which could then be compared to official data from the UK’s National Health Service on flu incidence by region.
The researchers deployed state-of-the art machine-learning algorithms that automatically figured out which keywords in the database of tweets were associated with elevated levels of flu.
Another case study in the research looked at levels of rainfall in a given location and time using the content of tweets.
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 flu outbreak or electoral voting intentions.
