Company or Institution

Bayero University, Kano, Nigeria, Bahir Dar University, Bahir Dar, Ethiopia, LIAAD INESC TEC, Porto, Portugal, and LT Group, Universität Hamburg

Industry

Internet

Website

https://afrihate.org

Country

Nigeria

Sustainable Development Goals (SDGs)

General description of the AI solution

Online hate is a growing problem across Africa. It inflicts harm on the people exposed to and targeted by it, pollutes and disrupts online communities and, in the worst cases, can be a precursor to physical violence. Machine learning tools for automatically finding and rating the hatefulness of online content can help to address this problem, supporting content moderation efforts, social media monitoring, and threat evaluation. However, at present, there are almost no hate detection tools available for any African languages, either in academia or industry. This means that African users of online services are more likely to not be protected against hate or to unfairly have their content moderated, which can severely restrict free expression and open use of the Internet.

Our project addresses this problem by introducing AfriHate, the first labelled dataset for online hate in Africa, covering 14 languages from 6 countries. We are also creating baseline machine learning models for each language, which will be made available to other researchers, civil society organisations and social media platforms to use. This is a first-of-its-kind project which has the potential to transform how online hate is understood, tackled and researched across Africa.

Publications

1. Analysis of the Ethiopic Twitter Dataset for Abusive Speech in Amharic

2. A Dataset for Hate Speech against Fulani Herdsmen in Nigeria

Needs