@inproceedings{akrah-pedersen-2023-duluthnlp,
title = "{D}uluth{NLP} at {S}em{E}val-2023 Task 12: {A}fri{S}enti-{S}em{E}val: Sentiment Analysis for Low-resource {A}frican Languages using {T}witter Dataset",
author = "Akrah, Samuel and
Pedersen, Ted",
editor = {Ojha, Atul Kr. and
Do{\u{g}}ru{\"o}z, A. Seza and
Da San Martino, Giovanni and
Tayyar Madabushi, Harish and
Kumar, Ritesh and
Sartori, Elisa},
booktitle = "Proceedings of the 17th International Workshop on Semantic Evaluation (SemEval-2023)",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.semeval-1.236",
doi = "10.18653/v1/2023.semeval-1.236",
pages = "1697--1701",
abstract = "This paper describes the DuluthNLP system that participated in Task 12 of SemEval-2023 on AfriSenti-SemEval: Sentiment Analysis for Low-resource African Languages using Twitter Dataset. Given a set of tweets, the task requires participating systems to classify each tweet as negative, positive or neutral. We evaluate a range of monolingual and multilingual pretrained models on the Twi language dataset, one among the 14 African languages included in the SemEval task. We introduce TwiBERT, a new pretrained model trained from scratch. We show that TwiBERT, along with mBERT, generally perform best when trained on the Twi dataset, achieving an F1 score of 64.29{\%} on the official evaluation test data, which ranks 14 out of 30 of the total submissions for Track 10. The TwiBERT model is released at \url{https://huggingface.co/sakrah/TwiBERT}",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="akrah-pedersen-2023-duluthnlp">
<titleInfo>
<title>DuluthNLP at SemEval-2023 Task 12: AfriSenti-SemEval: Sentiment Analysis for Low-resource African Languages using Twitter Dataset</title>
</titleInfo>
<name type="personal">
<namePart type="given">Samuel</namePart>
<namePart type="family">Akrah</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ted</namePart>
<namePart type="family">Pedersen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 17th International Workshop on Semantic Evaluation (SemEval-2023)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Atul</namePart>
<namePart type="given">Kr.</namePart>
<namePart type="family">Ojha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">A</namePart>
<namePart type="given">Seza</namePart>
<namePart type="family">Doğruöz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Giovanni</namePart>
<namePart type="family">Da San Martino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Harish</namePart>
<namePart type="family">Tayyar Madabushi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ritesh</namePart>
<namePart type="family">Kumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elisa</namePart>
<namePart type="family">Sartori</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper describes the DuluthNLP system that participated in Task 12 of SemEval-2023 on AfriSenti-SemEval: Sentiment Analysis for Low-resource African Languages using Twitter Dataset. Given a set of tweets, the task requires participating systems to classify each tweet as negative, positive or neutral. We evaluate a range of monolingual and multilingual pretrained models on the Twi language dataset, one among the 14 African languages included in the SemEval task. We introduce TwiBERT, a new pretrained model trained from scratch. We show that TwiBERT, along with mBERT, generally perform best when trained on the Twi dataset, achieving an F1 score of 64.29% on the official evaluation test data, which ranks 14 out of 30 of the total submissions for Track 10. The TwiBERT model is released at https://huggingface.co/sakrah/TwiBERT</abstract>
<identifier type="citekey">akrah-pedersen-2023-duluthnlp</identifier>
<identifier type="doi">10.18653/v1/2023.semeval-1.236</identifier>
<location>
<url>https://aclanthology.org/2023.semeval-1.236</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>1697</start>
<end>1701</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T DuluthNLP at SemEval-2023 Task 12: AfriSenti-SemEval: Sentiment Analysis for Low-resource African Languages using Twitter Dataset
%A Akrah, Samuel
%A Pedersen, Ted
%Y Ojha, Atul Kr.
%Y Doğruöz, A. Seza
%Y Da San Martino, Giovanni
%Y Tayyar Madabushi, Harish
%Y Kumar, Ritesh
%Y Sartori, Elisa
%S Proceedings of the 17th International Workshop on Semantic Evaluation (SemEval-2023)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F akrah-pedersen-2023-duluthnlp
%X This paper describes the DuluthNLP system that participated in Task 12 of SemEval-2023 on AfriSenti-SemEval: Sentiment Analysis for Low-resource African Languages using Twitter Dataset. Given a set of tweets, the task requires participating systems to classify each tweet as negative, positive or neutral. We evaluate a range of monolingual and multilingual pretrained models on the Twi language dataset, one among the 14 African languages included in the SemEval task. We introduce TwiBERT, a new pretrained model trained from scratch. We show that TwiBERT, along with mBERT, generally perform best when trained on the Twi dataset, achieving an F1 score of 64.29% on the official evaluation test data, which ranks 14 out of 30 of the total submissions for Track 10. The TwiBERT model is released at https://huggingface.co/sakrah/TwiBERT
%R 10.18653/v1/2023.semeval-1.236
%U https://aclanthology.org/2023.semeval-1.236
%U https://doi.org/10.18653/v1/2023.semeval-1.236
%P 1697-1701
Markdown (Informal)
[DuluthNLP at SemEval-2023 Task 12: AfriSenti-SemEval: Sentiment Analysis for Low-resource African Languages using Twitter Dataset](https://aclanthology.org/2023.semeval-1.236) (Akrah & Pedersen, SemEval 2023)
ACL