Researchers at India’s top engineering college have built an algorithm to filter fake social media rumours during national disasters

• Researchers at The Indian Institute of Technology (IIT) Kharagpur along with the Centre for Urban Science & Engineering at IIT-Bombay have developed an algorithm that will use artificial intelligence to filter the critical information on social media platforms during natural disasters including whatsapp, Facebook and Twitter.
  
• The solution is said to identify the rumours by mapping information sourced by the authorities, which will also help identify the users spreading misinformation.
  
• The algorithm was first tested on pilots over Twitter and WhatsApp at the time of Nepal earthquake in 2015 and Chennai floods in 2016.
• It is found that majority of tweets are a sympathetic content while only 2% is actually relevant.
  

Fake news via social media platforms has been a hotly debated topic for quite sometime now. Researchers at the Indian Institute of Technology (IIT) Kharagpur along with Centre for Urban Science & Engineering at IIT Bombay have developed an algorithm that will use artificial intelligence to filter the critical information during natural disasters on social media platforms including whatsapp, Facebook and Twitter, ET reported.

The algorithm can sort the social media posts and ensure that the data shared over the platforms is reliable and capable of being shared for relief operations. It is found that majority of tweets are a sympathetic content while only 2% is actually relevant.

With the help of this tool, the control room team will be able to fetch live updates about the resources needed and their availability. In addition, the rescue teams can be informed via phones.

Saptarshi Ghosh, who heads the tech team reportedly said that the algorithm, with the use of machine learning algorithm, can detect fake news and is able to alert the users during natural calamities. It is said to identify the rumours by mapping information sourced by the authorities, which will also help identify the users spreading misinformation.

However, the algorithm is limited to identifying disaster-related fake news only. It is able to provide upto 90% accuracy distinguishing real news and misinformation, Ghosh said.

If the proposal is passed, the team is expected to further collaborate with Microsoft Research and Qatar Computing Research Institute (QCRI) to develop the system.

Here’s what will happen when you tweet:

When you tweet an update on those affected by an earthquake in English or Hindi, the algo is said to identify the empathetic posts and send only the relevant information to the nearby rescue teams.

The algo was first tested on pilots over Twitter and WhatsApp at the time of Nepal earthquake in 2015 and Chennai floods in 2016.

The project was jointly funded by IIT Kharagpur’s Institute Scheme for Innovative Research and Development grant, Microsoft Research India and ITRA, Media Labs Asia and Department of Electronics and Information Technology.

SEE ALSO:
Hyper-nationalism behind India’s fake news menace: Report

WhatsApp is dramatically cutting message forwarding after viral fake news led to lynchings