“Have the worst flu, cold and headache!!” Tweets Jankii_x.

New research has found that social media could be used to track an event or phenomenon, such as flu outbreaks and rainfall rates.

The study by researchers from the University of Bristol’s Intelligent Systems Laboratory has found that social networks such as Facebook and microblogging services like Twitter have provided snapshots of real life by forming, electronically, public expression and interaction.

The research led by Professor Nello Cristianini and Vasileios Lampos geo-tagged user posts on the microblogging service of Twitter as their input data to investigate two case studies.

The first study looked at levels of rainfall in a given location and time using the contents of tweets.

"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,” said Cristianini.

The second study collected regional flu-like illness rates from tweets to find out if an epidemic was emerging.

“Wow. I cant remember the last time I was this sick…No work for me and I will be holed up in my room so I don't get anyone else sick...ugh,” post Doreen Territo Forni, on her Facebook status after mentioning that she was chewing on a glucose tablet to raise her blood sugar while suffering from a stomach virus.

The study builds upon previous research that reported a methodology using tweets to track flu-like illness rates in several UK regions, demonstrating a tool called, the Flu Detector, which uses the content of Twitter to map current flu rates in several UK regions.

"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 geolocated signals by selecting textual features that showed the content and understanding of the text."

Over the course of several months researchers were able to gather a database of over 50 million geo-located tweets, which could then be compared to that of official National Health Service data on flu incidents by region.

Researchers deployed machine-learning algorithms that automatically figured out which keywords in the tweet database were in connection with elevated levels of flu, which gave them an estimate of the severity of the flu in particular areas.

Although Twitter and Facebook users do not represent the general population, this study represents that social media can be used to track an event.

Elle Glazman, of New York told Medical Daily that lately, a lot of her Facebook friends were complaining about being sick.

“About 25-30% of the status updates on my wall were about people being sick with the cold or the flu in September and October.,” she said.

Future studies can focus on improving various subtasks in the methodology, enabling researchers to become more advanced at pinpointing situations, such as flu outbreaks or electoral voting intentions.