@inproceedings{hegde-etal-2022-corpus,
title = "Corpus Creation for Sentiment Analysis in Code-Mixed {T}ulu Text",
author = "Hegde, Asha and
Anusha, Mudoor Devadas and
Coelho, Sharal and
Shashirekha, Hosahalli Lakshmaiah and
Chakravarthi, Bharathi Raja",
booktitle = "Proceedings of the 1st Annual Meeting of the ELRA/ISCA Special Interest Group on Under-Resourced Languages",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.sigul-1.5",
pages = "33--40",
abstract = "Sentiment Analysis (SA) employing code-mixed data from social media helps in getting insights to the data and decision making for various applications. One such application is to analyze users{'} emotions from comments of videos on YouTube. Social media comments do not adhere to the grammatical norms of any language and they often comprise a mix of languages and scripts. The lack of annotated code-mixed data for SA in a low-resource language like Tulu makes the SA a challenging task. To address the lack of annotated code-mixed Tulu data for SA, a gold standard trlingual code-mixed Tulu annotated corpus of 7,171 YouTube comments is created. Further, Machine Learning (ML) algorithms are employed as baseline models to evaluate the developed dataset and the performance of the ML algorithms are found to be encouraging.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hegde-etal-2022-corpus">
<titleInfo>
<title>Corpus Creation for Sentiment Analysis in Code-Mixed Tulu Text</title>
</titleInfo>
<name type="personal">
<namePart type="given">Asha</namePart>
<namePart type="family">Hegde</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mudoor</namePart>
<namePart type="given">Devadas</namePart>
<namePart type="family">Anusha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sharal</namePart>
<namePart type="family">Coelho</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hosahalli</namePart>
<namePart type="given">Lakshmaiah</namePart>
<namePart type="family">Shashirekha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bharathi</namePart>
<namePart type="given">Raja</namePart>
<namePart type="family">Chakravarthi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 1st Annual Meeting of the ELRA/ISCA Special Interest Group on Under-Resourced Languages</title>
</titleInfo>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Sentiment Analysis (SA) employing code-mixed data from social media helps in getting insights to the data and decision making for various applications. One such application is to analyze users’ emotions from comments of videos on YouTube. Social media comments do not adhere to the grammatical norms of any language and they often comprise a mix of languages and scripts. The lack of annotated code-mixed data for SA in a low-resource language like Tulu makes the SA a challenging task. To address the lack of annotated code-mixed Tulu data for SA, a gold standard trlingual code-mixed Tulu annotated corpus of 7,171 YouTube comments is created. Further, Machine Learning (ML) algorithms are employed as baseline models to evaluate the developed dataset and the performance of the ML algorithms are found to be encouraging.</abstract>
<identifier type="citekey">hegde-etal-2022-corpus</identifier>
<location>
<url>https://aclanthology.org/2022.sigul-1.5</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>33</start>
<end>40</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Corpus Creation for Sentiment Analysis in Code-Mixed Tulu Text
%A Hegde, Asha
%A Anusha, Mudoor Devadas
%A Coelho, Sharal
%A Shashirekha, Hosahalli Lakshmaiah
%A Chakravarthi, Bharathi Raja
%S Proceedings of the 1st Annual Meeting of the ELRA/ISCA Special Interest Group on Under-Resourced Languages
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F hegde-etal-2022-corpus
%X Sentiment Analysis (SA) employing code-mixed data from social media helps in getting insights to the data and decision making for various applications. One such application is to analyze users’ emotions from comments of videos on YouTube. Social media comments do not adhere to the grammatical norms of any language and they often comprise a mix of languages and scripts. The lack of annotated code-mixed data for SA in a low-resource language like Tulu makes the SA a challenging task. To address the lack of annotated code-mixed Tulu data for SA, a gold standard trlingual code-mixed Tulu annotated corpus of 7,171 YouTube comments is created. Further, Machine Learning (ML) algorithms are employed as baseline models to evaluate the developed dataset and the performance of the ML algorithms are found to be encouraging.
%U https://aclanthology.org/2022.sigul-1.5
%P 33-40
Markdown (Informal)
[Corpus Creation for Sentiment Analysis in Code-Mixed Tulu Text](https://aclanthology.org/2022.sigul-1.5) (Hegde et al., SIGUL 2022)
ACL
- Asha Hegde, Mudoor Devadas Anusha, Sharal Coelho, Hosahalli Lakshmaiah Shashirekha, and Bharathi Raja Chakravarthi. 2022. Corpus Creation for Sentiment Analysis in Code-Mixed Tulu Text. In Proceedings of the 1st Annual Meeting of the ELRA/ISCA Special Interest Group on Under-Resourced Languages, pages 33–40, Marseille, France. European Language Resources Association.