A team at the International Institute of Information Technology, Hyderabad (IIIT-H) has developed a system that can detect hate speech on Twitter.
The automated system uses Artificial Intelligence chatterbots to detect racist and sexist comments and can automatically flag offensive content on the micro-blogging site.
Vasudeva Varma, Professor and Dean (R&D) at IIIT-H, his students Pinkesh Badjatiya, Shashank Gupta and adjunct faculty member Manish Gupta, developed the system at the institution's Informational and Retrieval Extraction Lab (IREL) after working on it for nearly a year.
Detecting hate speech can be helpful in not just filtering offensive content but also, as the team mentioned in its paper, in analyzing public sentiment of a group of users towards another group, and for discouraging associated wrongful activities."
How does the system work?
The team used a popular approach in machine learning called supervised learning.
"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 is smart enough to recognize racism or sexism in text, if it sees one. The algorithm uses neural networks, more popularly called as deep learning. These algorithms are inspired from the human brain, and they try to simulate how humans learn from examples," the developers explained in a statement.
Earlier this month, they presented their work at the World Wide Web Conference (WWW2017) in Perth. Their poster on Deep Learning for Hate Speech Detection in Twitter was voted as the best poster presentation among 166 submissions from around the world.
"This is a very prestigious conference since many of the policies regarding the Internet are formulated here. And itâ€™s very well attended by academia and research wings of large companies like Facebook, Google, and Microsoft etc. Also the fact that weâ€™ve been able to make it through the rigorous review process to have our poster presentation voted as the best is a great validation of our research work," said Vasudeva Varma.