Research

Engineering Sciences

Title :

Toward promoting a safe and peaceful online world: Deep neural multilingual models to combat online hate content

Area of research :

Engineering Sciences

Principal Investigator :

Dr. Animesh Mukherjee, Indian Institute Of Technology (IIT) Kharagpur, West Bengal

Timeline Start Year :

2024

Timeline End Year :

2027

Contact info :

Equipments :

Details

Executive Summary :

Hate speech, which spreads online and offline, has led to the implementation of laws and policies to prevent violence based on various factors. This has affected both online and offline communities, causing trauma and psychological distress for victims. In 2019, the United Nations released a strategy and plan of action on hate speech, focusing on monitoring and analyzing hate speech, using technology to combat it, and countering hate speech. The advisory committee emphasized the importance of prompt detection and combating hate speech to create neutral and safe content and prevent serious real-life consequences. The project aims to analyze how hate speech spreads online, detect it using computer algorithms, and mitigate it by using more speech to counter hate speech. The goal is to resolve these issues to ensure peace and safety in the online world. The project aims to explore the speed and depth of hate speech spread, the effectiveness of detection methods, and the use of counterspeech, which can be generic or specific to target communities.

Total Budget (INR):

25,55,300

Organizations involved