@inproceedings{advani-etal-2020-c1,
title = "C1 at {S}em{E}val-2020 Task 9: {S}enti{M}ix: Sentiment Analysis for Code-Mixed Social Media Text Using Feature Engineering",
author = "Advani, Laksh and
Lu, Clement and
Maharjan, Suraj",
editor = "Herbelot, Aurelie and
Zhu, Xiaodan and
Palmer, Alexis and
Schneider, Nathan and
May, Jonathan and
Shutova, Ekaterina",
booktitle = "Proceedings of the Fourteenth Workshop on Semantic Evaluation",
month = dec,
year = "2020",
address = "Barcelona (online)",
publisher = "International Committee for Computational Linguistics",
url = "https://aclanthology.org/2020.semeval-1.163",
doi = "10.18653/v1/2020.semeval-1.163",
pages = "1227--1232",
abstract = "In today{'}s interconnected and multilingual world, code-mixing of languages on social media is a common occurrence. While many Natural Language Processing (NLP) tasks like sentiment analysis are mature and well designed for monolingual text, techniques to apply these tasks to code-mixed text still warrant exploration. This paper describes our feature engineering approach to sentiment analysis in code-mixed social media text for SemEval-2020 Task 9: SentiMix. We tackle this problem by leveraging a set of hand-engineered lexical, sentiment, and metadata fea- tures to design a classifier that can disambiguate between {``}positive{''}, {``}negative{''} and {``}neutral{''} sentiment. With this model we are able to obtain a weighted F1 score of 0.65 for the {``}Hinglish{''} task and 0.63 for the {``}Spanglish{''} tasks.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="advani-etal-2020-c1">
<titleInfo>
<title>C1 at SemEval-2020 Task 9: SentiMix: Sentiment Analysis for Code-Mixed Social Media Text Using Feature Engineering</title>
</titleInfo>
<name type="personal">
<namePart type="given">Laksh</namePart>
<namePart type="family">Advani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Clement</namePart>
<namePart type="family">Lu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Suraj</namePart>
<namePart type="family">Maharjan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fourteenth Workshop on Semantic Evaluation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Aurelie</namePart>
<namePart type="family">Herbelot</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaodan</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexis</namePart>
<namePart type="family">Palmer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nathan</namePart>
<namePart type="family">Schneider</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jonathan</namePart>
<namePart type="family">May</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Shutova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Committee for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Barcelona (online)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In today’s interconnected and multilingual world, code-mixing of languages on social media is a common occurrence. While many Natural Language Processing (NLP) tasks like sentiment analysis are mature and well designed for monolingual text, techniques to apply these tasks to code-mixed text still warrant exploration. This paper describes our feature engineering approach to sentiment analysis in code-mixed social media text for SemEval-2020 Task 9: SentiMix. We tackle this problem by leveraging a set of hand-engineered lexical, sentiment, and metadata fea- tures to design a classifier that can disambiguate between “positive”, “negative” and “neutral” sentiment. With this model we are able to obtain a weighted F1 score of 0.65 for the “Hinglish” task and 0.63 for the “Spanglish” tasks.</abstract>
<identifier type="citekey">advani-etal-2020-c1</identifier>
<identifier type="doi">10.18653/v1/2020.semeval-1.163</identifier>
<location>
<url>https://aclanthology.org/2020.semeval-1.163</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>1227</start>
<end>1232</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T C1 at SemEval-2020 Task 9: SentiMix: Sentiment Analysis for Code-Mixed Social Media Text Using Feature Engineering
%A Advani, Laksh
%A Lu, Clement
%A Maharjan, Suraj
%Y Herbelot, Aurelie
%Y Zhu, Xiaodan
%Y Palmer, Alexis
%Y Schneider, Nathan
%Y May, Jonathan
%Y Shutova, Ekaterina
%S Proceedings of the Fourteenth Workshop on Semantic Evaluation
%D 2020
%8 December
%I International Committee for Computational Linguistics
%C Barcelona (online)
%F advani-etal-2020-c1
%X In today’s interconnected and multilingual world, code-mixing of languages on social media is a common occurrence. While many Natural Language Processing (NLP) tasks like sentiment analysis are mature and well designed for monolingual text, techniques to apply these tasks to code-mixed text still warrant exploration. This paper describes our feature engineering approach to sentiment analysis in code-mixed social media text for SemEval-2020 Task 9: SentiMix. We tackle this problem by leveraging a set of hand-engineered lexical, sentiment, and metadata fea- tures to design a classifier that can disambiguate between “positive”, “negative” and “neutral” sentiment. With this model we are able to obtain a weighted F1 score of 0.65 for the “Hinglish” task and 0.63 for the “Spanglish” tasks.
%R 10.18653/v1/2020.semeval-1.163
%U https://aclanthology.org/2020.semeval-1.163
%U https://doi.org/10.18653/v1/2020.semeval-1.163
%P 1227-1232
Markdown (Informal)
[C1 at SemEval-2020 Task 9: SentiMix: Sentiment Analysis for Code-Mixed Social Media Text Using Feature Engineering](https://aclanthology.org/2020.semeval-1.163) (Advani et al., SemEval 2020)
ACL