AfriSenti: a twitter sentiment analysis benchmark for African languages

From National Research Council Canada

Download	View final version: AfriSenti: a twitter sentiment analysis benchmark for African languages (PDF, 1.4 MiB)
DOI	Resolve DOI: https://doi.org/10.18653/v1/2023.emnlp-main.862
Author	Search for: Muhammad, Shamsuddeen; Search for: Abdulmumin, Idris; Search for: Ayele, Abinew; Search for: Ousidhoum, Nedjma; Search for: Adelani, David; Search for: Yimam, Seid; Search for: Ahmad, Ibrahim; Search for: Beloucif, Meriem; Search for: Mohammad, Saif¹; Search for: Ruder, Sebastian; Search for: Hourrane, Oumaima; Search for: Jorge, Alipio; Search for: Brazdil, Pavel; Search for: Ali, Felermino; Search for: David, Davis; Search for: Osei, Salomey; Search for: Shehu-Bello, Bello; Search for: Lawan, Falalu; Search for: Gwadabe, Tajuddeen; Search for: Rutunda, Samuel; Search for: Belay, Tadesse; Search for: Messelle, Wendimu; Search for: Balcha, Hailu; Search for: Chala, Sisay; Search for: Gebremichael, Hagos; Search for: Opoku, Bernard; Search for: Arthur, Stephen
Affiliation	National Research Council Canada. Digital Technologies
Format	Text, Article
Conference	2023 Conference on Empirical Methods in Natural Language Processing, December 6-10, 2023, Singapore
Abstract	Africa is home to over 2,000 languages from over six language families and has the highest linguistic diversity among all continents. This includes 75 languages with at least one million speakers each. Yet, there is little NLP research conducted on African languages. Crucial in enabling such research is the availability of high-quality annotated datasets. In this paper, we introduce AfriSenti, a sentiment analysis benchmark that contains a total of >110,000 tweets in 14 African languages (Amharic, Algerian Arabic, Hausa, Igbo, Kinyarwanda, Moroccan Arabic, Mozambican Portuguese, Nigerian Pidgin, Oromo, Swahili, Tigrinya, Twi, Xitsonga, and Yoruba) from four language families. The tweets were annotated by native speakers and used in the AfriSenti-SemEval shared task (with over 200 participants, see website: https://afrisenti-semeval.github.io). We describe the data collection methodology, annotation process, and the challenges we dealt with when curating each dataset. We further report baseline experiments conducted on the AfriSenti datasets and discuss their usefulness.
Publication date	2023-12-06
Publisher	Association for Computational Linguistics
Licence	Creative Commons Attribution 4.0 International (CC BY 4.0) https://creativecommons.org/licenses/by/4.0/
In	Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing (6 December 2023): 13968–13981. https://doi.org/10.18653/v1/2023.emnlp-main.
Language	English
Peer reviewed	Yes
Export citation	Export as RIS
Report a correction	Report a correction (opens in a new tab)
Record identifier	31b058c0-af49-46ba-8e74-e1c67c14a16b
Record created	2024-01-08
Record modified	2024-01-09

Date modified:: 2026-01-16