Real news or fake? Soon, it's going to be easy to weed out fake news with a simple tool created by the the Information Retrieval and Extraction Lab (IREL) at the Indian Institute of Information Technology, Hyderabad. Say hello to the 'Fake-o-Meter'.
A few years ago, IIIT-Hyderabad faculty members collaborated with industry experts to create ‘Confluence’, a team to focus on the relevant issues in the IT industry.
“We were in search of industry-enabling and consumable solutions. This industry-institute connect is what Vasu and I have demonstrated over the last four months,” says J Ramachandran, Founder and CEO of Gramener, a data-visualsation startup. Ramachandran leads the team along with Prof Vasudeva Varma.
In this world of social media and fake news, IIIT-Hyderabad’s Information Retrieval and Extraction Lab( IREL) has launched a tool known as ‘Fake-o-Meter’ to differentiate between authentic information and fake news. How do they do it?
Prof Varma explains,
“There’s content out there with an intentionally wrong motive, technically labelled as disinformation as well as misinformation, which is just wrong content. The virality of content itself is often times a sheer giveaway about its authenticity.”
How it works
It is a web engine where one can copy the tweet or headline of a news story and submit it to the Fake-o-meter to get a colour-coded response on its authenticity in percentage terms. News that has a low probability of being fake is coded green with lower percentages. On the other hand, higher percentages are coded red indicating high degree of fakeness.
This is done with the help of machine learning algorithms and NLP (natural language processing) which look at the actual content itself and the manner in which the context is being propagated.
The tool works for many languages, including Spanish and Chinese, and includes various forms of online content, ranging from blogs and news stories to tweets, bizarre news, hate speech, and click-bait, etc.
Prof Varma, who is also the CEO of CIE, says Fake-o-Meter can be helpful for an editor who would otherwise process one-two stories a day, to process around 50 stories a day.
“A 50-fold productivity enhancement is being brought about by these tools and techniques. That’s the value we are bringing.”
The Confluence team is currently working on other solutions such as summarisation and cross-purposing solutions, both of which are expected to be disruptive in industry.
According to Ramachandran, “Common mental models between people, whether it is for information consumption, or authentication and summarisation, all help people understand each other, hence productivity goes up in every human enterprise. And overall humanity is what that gains.”