@inproceedings{muhammad-etal-2023-afrisenti,
title = "{A}fri{S}enti: A {T}witter Sentiment Analysis Benchmark for {A}frican Languages",
author = "Muhammad, Shamsuddeen Hassan and
Abdulmumin, Idris and
Ayele, Abinew Ali and
Ousidhoum, Nedjma and
Adelani, David Ifeoluwa and
Yimam, Seid Muhie and
Ahmad, Ibrahim Sa'id and
Beloucif, Meriem and
Mohammad, Saif M. and
Ruder, Sebastian and
Hourrane, Oumaima and
Brazdil, Pavel and
Jorge, Alipio and
Ali, Felermino D{\'a}rio M{\'a}rio Ant{\'o}nio and
David, Davis and
Osei, Salomey and
Shehu Bello, Bello and
Ibrahim, Falalu and
Gwadabe, Tajuddeen and
Rutunda, Samuel and
Belay, Tadesse and
Messelle, Wendimu Baye and
Balcha, Hailu Beshada and
Chala, Sisay Adugna and
Gebremichael, Hagos Tesfahun and
Opoku, Bernard and
Arthur, Stephen",
editor = "Bouamor, Houda and
Pino, Juan and
Bali, Kalika",
booktitle = "Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.emnlp-main.862/",
doi = "10.18653/v1/2023.emnlp-main.862",
pages = "13968--13981",
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 {\ensuremath{>}}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."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="muhammad-etal-2023-afrisenti">
<titleInfo>
<title>AfriSenti: A Twitter Sentiment Analysis Benchmark for African Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shamsuddeen</namePart>
<namePart type="given">Hassan</namePart>
<namePart type="family">Muhammad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Idris</namePart>
<namePart type="family">Abdulmumin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abinew</namePart>
<namePart type="given">Ali</namePart>
<namePart type="family">Ayele</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nedjma</namePart>
<namePart type="family">Ousidhoum</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="given">Ifeoluwa</namePart>
<namePart type="family">Adelani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seid</namePart>
<namePart type="given">Muhie</namePart>
<namePart type="family">Yimam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ibrahim</namePart>
<namePart type="given">Sa’id</namePart>
<namePart type="family">Ahmad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Meriem</namePart>
<namePart type="family">Beloucif</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Saif</namePart>
<namePart type="given">M</namePart>
<namePart type="family">Mohammad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sebastian</namePart>
<namePart type="family">Ruder</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Oumaima</namePart>
<namePart type="family">Hourrane</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pavel</namePart>
<namePart type="family">Brazdil</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alipio</namePart>
<namePart type="family">Jorge</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Felermino</namePart>
<namePart type="given">Dário</namePart>
<namePart type="given">Mário</namePart>
<namePart type="given">António</namePart>
<namePart type="family">Ali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Davis</namePart>
<namePart type="family">David</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Salomey</namePart>
<namePart type="family">Osei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bello</namePart>
<namePart type="family">Shehu Bello</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Falalu</namePart>
<namePart type="family">Ibrahim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tajuddeen</namePart>
<namePart type="family">Gwadabe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Samuel</namePart>
<namePart type="family">Rutunda</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tadesse</namePart>
<namePart type="family">Belay</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wendimu</namePart>
<namePart type="given">Baye</namePart>
<namePart type="family">Messelle</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hailu</namePart>
<namePart type="given">Beshada</namePart>
<namePart type="family">Balcha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sisay</namePart>
<namePart type="given">Adugna</namePart>
<namePart type="family">Chala</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hagos</namePart>
<namePart type="given">Tesfahun</namePart>
<namePart type="family">Gebremichael</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bernard</namePart>
<namePart type="family">Opoku</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stephen</namePart>
<namePart type="family">Arthur</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="family">Pino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kalika</namePart>
<namePart type="family">Bali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<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 \ensuremath>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.</abstract>
<identifier type="citekey">muhammad-etal-2023-afrisenti</identifier>
<identifier type="doi">10.18653/v1/2023.emnlp-main.862</identifier>
<location>
<url>https://aclanthology.org/2023.emnlp-main.862/</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>13968</start>
<end>13981</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T AfriSenti: A Twitter Sentiment Analysis Benchmark for African Languages
%A Muhammad, Shamsuddeen Hassan
%A Abdulmumin, Idris
%A Ayele, Abinew Ali
%A Ousidhoum, Nedjma
%A Adelani, David Ifeoluwa
%A Yimam, Seid Muhie
%A Ahmad, Ibrahim Sa’id
%A Beloucif, Meriem
%A Mohammad, Saif M.
%A Ruder, Sebastian
%A Hourrane, Oumaima
%A Brazdil, Pavel
%A Jorge, Alipio
%A Ali, Felermino Dário Mário António
%A David, Davis
%A Osei, Salomey
%A Shehu Bello, Bello
%A Ibrahim, Falalu
%A Gwadabe, Tajuddeen
%A Rutunda, Samuel
%A Belay, Tadesse
%A Messelle, Wendimu Baye
%A Balcha, Hailu Beshada
%A Chala, Sisay Adugna
%A Gebremichael, Hagos Tesfahun
%A Opoku, Bernard
%A Arthur, Stephen
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F muhammad-etal-2023-afrisenti
%X 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 \ensuremath>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.
%R 10.18653/v1/2023.emnlp-main.862
%U https://aclanthology.org/2023.emnlp-main.862/
%U https://doi.org/10.18653/v1/2023.emnlp-main.862
%P 13968-13981
Markdown (Informal)
[AfriSenti: A Twitter Sentiment Analysis Benchmark for African Languages](https://aclanthology.org/2023.emnlp-main.862/) (Muhammad et al., EMNLP 2023)
ACL
- Shamsuddeen Hassan Muhammad, Idris Abdulmumin, Abinew Ali Ayele, Nedjma Ousidhoum, David Ifeoluwa Adelani, Seid Muhie Yimam, Ibrahim Sa'id Ahmad, Meriem Beloucif, Saif M. Mohammad, Sebastian Ruder, Oumaima Hourrane, Pavel Brazdil, Alipio Jorge, Felermino Dário Mário António Ali, Davis David, Salomey Osei, Bello Shehu Bello, Falalu Ibrahim, Tajuddeen Gwadabe, Samuel Rutunda, Tadesse Belay, Wendimu Baye Messelle, Hailu Beshada Balcha, Sisay Adugna Chala, Hagos Tesfahun Gebremichael, Bernard Opoku, and Stephen Arthur. 2023. AfriSenti: A Twitter Sentiment Analysis Benchmark for African Languages. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 13968–13981, Singapore. Association for Computational Linguistics.