@inproceedings{etori-gini-2024-rideke,
title = "{R}ide{KE}: Leveraging Low-resource {T}witter User-generated Content for Sentiment and Emotion Detection on Code-switched {RHS} Dataset.",
author = "Etori, Naome and
Gini, Maria",
editor = "De Clercq, Orph{\'e}e and
Barriere, Valentin and
Barnes, Jeremy and
Klinger, Roman and
Sedoc, Jo{\~a}o and
Tafreshi, Shabnam",
booktitle = "Proceedings of the 14th Workshop on Computational Approaches to Subjectivity, Sentiment, {\&} Social Media Analysis",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.wassa-1.19",
pages = "234--249",
abstract = "Social media has become a crucial open-access platform enabling individuals to freely express opinions and share experiences. These platforms contain user-generated content facilitating instantaneous communication and feedback. However, leveraging low-resource language data from Twitter can be challenging due to the scarcity and poor quality of content with significant variations in language use, such as slang and code-switching. Automatically identifying tweets in low-resource languages can also be challenging because Twitter primarily supports high-resource languages; low-resource languages often lack robust linguistic and contextual support. This paper analyzes Kenyan code-switched data from Twitter using four transformer-based pretrained models for sentiment and emotion classification tasks using supervised and semi-supervised methods. We detail the methodology behind data collection, the annotation procedure, and the challenges encountered during the data curation phase. Our results show that XLM-R outperforms other models; for sentiment analysis, XLM-R supervised model achieves the highest accuracy (69.2{\%}) and F1 score (66.1{\%}), XLM-R semi-supervised (67.2{\%} accuracy, 64.1{\%} F1 score). In emotion analysis, DistilBERT supervised leads in accuracy (59.8{\%}) and F1 score (31{\%}), mBERT semi-supervised (accuracy (59{\%} and F1 score 26.5{\%}). AfriBERTa models show the lowest accuracy and F1 scores. This indicates that the semi-supervised method{'}s performance is constrained by the small labeled dataset.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="etori-gini-2024-rideke">
<titleInfo>
<title>RideKE: Leveraging Low-resource Twitter User-generated Content for Sentiment and Emotion Detection on Code-switched RHS Dataset.</title>
</titleInfo>
<name type="personal">
<namePart type="given">Naome</namePart>
<namePart type="family">Etori</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Gini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 14th Workshop on Computational Approaches to Subjectivity, Sentiment, & Social Media Analysis</title>
</titleInfo>
<name type="personal">
<namePart type="given">Orphée</namePart>
<namePart type="family">De Clercq</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Valentin</namePart>
<namePart type="family">Barriere</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jeremy</namePart>
<namePart type="family">Barnes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roman</namePart>
<namePart type="family">Klinger</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">João</namePart>
<namePart type="family">Sedoc</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shabnam</namePart>
<namePart type="family">Tafreshi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Social media has become a crucial open-access platform enabling individuals to freely express opinions and share experiences. These platforms contain user-generated content facilitating instantaneous communication and feedback. However, leveraging low-resource language data from Twitter can be challenging due to the scarcity and poor quality of content with significant variations in language use, such as slang and code-switching. Automatically identifying tweets in low-resource languages can also be challenging because Twitter primarily supports high-resource languages; low-resource languages often lack robust linguistic and contextual support. This paper analyzes Kenyan code-switched data from Twitter using four transformer-based pretrained models for sentiment and emotion classification tasks using supervised and semi-supervised methods. We detail the methodology behind data collection, the annotation procedure, and the challenges encountered during the data curation phase. Our results show that XLM-R outperforms other models; for sentiment analysis, XLM-R supervised model achieves the highest accuracy (69.2%) and F1 score (66.1%), XLM-R semi-supervised (67.2% accuracy, 64.1% F1 score). In emotion analysis, DistilBERT supervised leads in accuracy (59.8%) and F1 score (31%), mBERT semi-supervised (accuracy (59% and F1 score 26.5%). AfriBERTa models show the lowest accuracy and F1 scores. This indicates that the semi-supervised method’s performance is constrained by the small labeled dataset.</abstract>
<identifier type="citekey">etori-gini-2024-rideke</identifier>
<location>
<url>https://aclanthology.org/2024.wassa-1.19</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>234</start>
<end>249</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T RideKE: Leveraging Low-resource Twitter User-generated Content for Sentiment and Emotion Detection on Code-switched RHS Dataset.
%A Etori, Naome
%A Gini, Maria
%Y De Clercq, Orphée
%Y Barriere, Valentin
%Y Barnes, Jeremy
%Y Klinger, Roman
%Y Sedoc, João
%Y Tafreshi, Shabnam
%S Proceedings of the 14th Workshop on Computational Approaches to Subjectivity, Sentiment, & Social Media Analysis
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F etori-gini-2024-rideke
%X Social media has become a crucial open-access platform enabling individuals to freely express opinions and share experiences. These platforms contain user-generated content facilitating instantaneous communication and feedback. However, leveraging low-resource language data from Twitter can be challenging due to the scarcity and poor quality of content with significant variations in language use, such as slang and code-switching. Automatically identifying tweets in low-resource languages can also be challenging because Twitter primarily supports high-resource languages; low-resource languages often lack robust linguistic and contextual support. This paper analyzes Kenyan code-switched data from Twitter using four transformer-based pretrained models for sentiment and emotion classification tasks using supervised and semi-supervised methods. We detail the methodology behind data collection, the annotation procedure, and the challenges encountered during the data curation phase. Our results show that XLM-R outperforms other models; for sentiment analysis, XLM-R supervised model achieves the highest accuracy (69.2%) and F1 score (66.1%), XLM-R semi-supervised (67.2% accuracy, 64.1% F1 score). In emotion analysis, DistilBERT supervised leads in accuracy (59.8%) and F1 score (31%), mBERT semi-supervised (accuracy (59% and F1 score 26.5%). AfriBERTa models show the lowest accuracy and F1 scores. This indicates that the semi-supervised method’s performance is constrained by the small labeled dataset.
%U https://aclanthology.org/2024.wassa-1.19
%P 234-249
Markdown (Informal)
[RideKE: Leveraging Low-resource Twitter User-generated Content for Sentiment and Emotion Detection on Code-switched RHS Dataset.](https://aclanthology.org/2024.wassa-1.19) (Etori & Gini, WASSA-WS 2024)
ACL