A first of its kind software that can detect hate speech on micro blogging site Twitter has been developed by a team at the International Institute of Information Technology, Hyderabad (IIIT-H). The team comprises Vasudeva Varma, professor and dean (R&D) at IIIT-H, students Pinkesh Badjatiya and Shashank Gupta, and another member named Manish Gupta. The team was working on the project for around a year’s time. The project involved detailed analysis of deep learning for hate speech, as relevant to micro blogging site Twitter.
The team said that the software has the capability to identify abusive language, sexist and racist speech. It can also be used to flag offensive content. Furthermore, it can be used to analyze public sentiment and identify the root cause of the problem. Speaking about the software, Varma said, “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 categorized 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 is smart enough to recognize racism or sexism in a text. 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.”