Back

 Industry News Details

 
IIIT-H team develops hate speech detector to track offensive tweets Posted on : Apr 28 - 2017

A team from the International Institute of Information Technology, Hyderabad, (IIIT-H) has developed a system to detect hate speech on microblogging site Twitter, a first of its kind.

The team includes Vasudeva Varma, professor and dean (R&D) at IIIT-H, students Pinkesh Badjatiya and Shashank Gupta, and adjunct faculty Manish Gupta. They were working on the topic of 'deep learning for hate speech' on micro blogging site Twitter for close to a year.

The team says the system can detect abusive language, sexist and racist speech and flag offensive content. This is useful in filtering such content, and also analysing public sentiment to get to the root of the problem.

"To detect hate speech+ , a popular approach called supervised learning is used. Essentially a computer algorithm is fed many examples of text from each form of hate, which can be categorised as `racist' or `sexist' tweets. The algorithm is designed in such a way that it learns as it sees the data, and after the algorithm terminates, the program me is smart enough to recognise racism or sexism in a text," said Varma. "The algorithm uses neural networks, more popularly called deep learning. These algorithms are inspired from the human brain, and they try to simulate how humans learn from examples," he said.

This line of research is highly relevant in the current wave of social media, but has its unique challenges and complexities, team members said. The research was conducted at the IIIT-H's Informational and Retrieval Extraction Lab (IREL) by using natural language processing, semantics and artificial intelligence. Source