Filtering the fake news about disasters on social media platforms like Twitter, Facebook and WhatsApp are going to very simpler.
The Indian Institution of Technology (IIT) Kharagpur has come with a solution which uses artificial intelligence (AI) to extract critical information from social media platforms (such as Facebook, Twitter, and WhatsApp) is too difficult to obtain manually. This information can use to determine the authenticity of the posts.
In the time of Chennai floods in 2016, there were a lot of rumors that crocodiles had escaped from the park. IIT Kharagpur’s solution could easily identify this problem as fake news by mapping and analyzing the information emanating from authorities in the region.
“Our solution can detect fake news and can even alert users in the time of disasters via deep machine learning algorithms,” said Saptarshi Ghose of the Department of Computer Science & Engineering at IIT Kharagpur.
This method is limited only to disaster in terms of identifying fake or rumors news. Ghose told that this method is capable of at least 90% accuracy in distinguishing rumor news from real.
In addition, this solution helps to take information that can help victims of disasters. It is admired that only 2% of tweets have important information on disasters when the remaining content is largely conversations, mostly sympathy of victims.
This Is How It Works:
When one tweets about the situation of victim hit by an earthquake in Hindi or English, a computer program can read via empathetic post and send the important information to relief operators nearby.
“We are developing artificial intelligence (AI) methods to extract specific types of critical and actionable information from social media content posted in disasters such as resource needs, resource availability and information about trapped people,” said Ghosh.
The institute started with the pilot on WhatsApp and Twitter in the 2015 Nepal earthquake and the 2016 Chennai floods. The project was jointly supported by IIT Kharagpur’s Institution Scheme for Innovation Research and DEvelopment grant, Microsoft Research India and ITRA, Media Labs Asia and Department of Electronics and Information Technology.
This institute along with its associates at Qatar Computing Research Institute (QCRI) has submitted a proposal to Microsoft research India.
“If this proposal gets accepted, we will collaborate with Microsoft Research and QCRI to develop the systems for aiding post-disaster relief operations,” said by Ghose.
The next step for the institute is to grow web-based systems for aiding post-disaster relief operations.
“These web-based systems will utilize the algorithms developed by us and perform tasks like identifying and extracting actionable information, summarising the actionable information,” Ghose added.
A person can be sitting in the control room to get a live update about what resources are needed and where they are available and coordinate relief operations accordingly.
Or a relief worker can be updated through smartphone about caught people so that they can be rescued.
IIT Kharagpur, with the Centre for Urban Science And Engineering at IIT Bombay, has also submitted a project proposal to the Department Of Science & Technology.
“As part of this project, we wish to focus on emergency situations in urban areas, example- the recent floods in Mumbai and Chennai,” Ghose said.
Do you like it? Don’t forget to share it.