Skip to main content
Go to the home page of the European Commission (opens in new window)
English en
CORDIS - EU research results
CORDIS

Responsive classifiers against hate speech in low-resource settings

Project description

Extending hate speech filtering to low-resource regions

In the age of social media, hate speech has become an alarming global issue. While tech giants employ machine learning models to filter such content, most languages remain underserved due to a lack of training data. In this context, the ERC-funded Respond2Hate project will develop multilingual representation models. Its aim is to create a user-friendly browser extension, enabling individuals to independently locally eliminate hateful content from their social media feeds. Specifically, Respond2Hate focuses on developing nimble, adaptive models requiring minimal initial training data, using cutting-edge Natural Language Processing and deep learning techniques. By extending hate speech filtering to low-resource regions often overlooked by governments and NGOs, this project empowers users to curate their online experience.

Objective

"Hate speech is a worldwide phenomenon that is increasingly pervading online spaces, creating an unsafe environment for users. While tech companies address this problem by server-side filtering using machine learning models trained on large datasets, these automatic methods cannot be applied to most languages due to lack of available training data.

Based on recent results of the PI's ERC project on multilingual representation models in low-resource settings, Respond2Hate aims at developing a pilot browser extension that allows users to locally remove hateful content from their social media feeds themselves, without having to rely on the support of tech companies.

Since hate speech is highly dependent on cultural context, responsive classifiers are needed that adapt to the individual environment. Commercial efforts focus on large-scale, general-purpose models which are often burdened with representation and bias problems, and therefore cope poorly with swiftly changing targets or information shift between regional contexts. In contrast, we seek to develop lightweight, adaptive models that require only a small dataset for initial fine-tuning by continuously enhancing model capabilities over time.

This is achieved by applying state-of-the-art Natural Language Processing (NLP) and deep learning techniques for pre-trained language models like low-resource transfer of hate speech representations from high-resource languages and few-shot learning based on limited user feedback. We have already successfully applied these methods in low-resource multilingual settings, and will now validate their use for hate speech filtering.

By making hate speech detection and reduction available in ""low-resource"" countries with little representation in current training datasets, which are currently not served well by governments, industry and NGOs, Respond2Hate will empower users to self-control their exposure to hate speech, fostering a healthier and safer online environment."

Fields of science (EuroSciVoc)

Programme(s)

Topic(s)

Funding Scheme

HORIZON-ERC-POC - HORIZON ERC Proof of Concept Grants

See all projects funded under this funding scheme

Call for proposal

(opens in new window) ERC-2022-POC2

See all projects funded under this call

Host institution

LUDWIG-MAXIMILIANS-UNIVERSITAET MUENCHEN
Net EU contribution
€ 150 000,00
Address
GESCHWISTER SCHOLL PLATZ 1
80539 Planegg
Germany
Region
Bayern Oberbayern München, Kreisfreie Stadt
Activity type
Higher or Secondary Education Establishments
Links
Total cost
No data

Beneficiaries (1)