@inproceedings{roychoudhury-naskar-2021-fine,
title = "Fine-tuning {BERT} to classify {COVID}19 tweets containing symptoms",
author = "Roychoudhury, Rajarshi and
Naskar, Sudip",
editor = "Magge, Arjun and
Klein, Ari and
Miranda-Escalada, Antonio and
Al-garadi, Mohammed Ali and
Alimova, Ilseyar and
Miftahutdinov, Zulfat and
Farre-Maduell, Eulalia and
Lopez, Salvador Lima and
Flores, Ivan and
O'Connor, Karen and
Weissenbacher, Davy and
Tutubalina, Elena and
Sarker, Abeed and
Banda, Juan M and
Krallinger, Martin and
Gonzalez-Hernandez, Graciela",
booktitle = "Proceedings of the Sixth Social Media Mining for Health ({\#}SMM4H) Workshop and Shared Task",
month = jun,
year = "2021",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.smm4h-1.30",
doi = "10.18653/v1/2021.smm4h-1.30",
pages = "138--140",
abstract = "Twitter is a valuable source of patient-generated data that has been used in various population health studies. The first step in many of these studies is to identify and capture Twitter messages (tweets) containing medication mentions. Identifying personal mentions of COVID19 symptoms requires distinguishing personal mentions from other mentions such as symptoms reported by others and references to news articles or other sources. In this article, we describe our submission to Task 6 of the Social Media Mining for Health Applications (SMM4H) Shared Task 2021. This task challenged participants to classify tweets where the target classes are:(1) self-reports,(2) non-personal reports, and (3) literature/news mentions. Our system used a handcrafted preprocessing and word embeddings from BERT encoder model. We achieved an F1 score of 93{\%}",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="roychoudhury-naskar-2021-fine">
<titleInfo>
<title>Fine-tuning BERT to classify COVID19 tweets containing symptoms</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rajarshi</namePart>
<namePart type="family">Roychoudhury</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sudip</namePart>
<namePart type="family">Naskar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Sixth Social Media Mining for Health (#SMM4H) Workshop and Shared Task</title>
</titleInfo>
<name type="personal">
<namePart type="given">Arjun</namePart>
<namePart type="family">Magge</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ari</namePart>
<namePart type="family">Klein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Miranda-Escalada</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammed</namePart>
<namePart type="given">Ali</namePart>
<namePart type="family">Al-garadi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ilseyar</namePart>
<namePart type="family">Alimova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zulfat</namePart>
<namePart type="family">Miftahutdinov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eulalia</namePart>
<namePart type="family">Farre-Maduell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Salvador</namePart>
<namePart type="given">Lima</namePart>
<namePart type="family">Lopez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ivan</namePart>
<namePart type="family">Flores</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Karen</namePart>
<namePart type="family">O’Connor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Davy</namePart>
<namePart type="family">Weissenbacher</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elena</namePart>
<namePart type="family">Tutubalina</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abeed</namePart>
<namePart type="family">Sarker</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="given">M</namePart>
<namePart type="family">Banda</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Martin</namePart>
<namePart type="family">Krallinger</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Graciela</namePart>
<namePart type="family">Gonzalez-Hernandez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mexico City, Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Twitter is a valuable source of patient-generated data that has been used in various population health studies. The first step in many of these studies is to identify and capture Twitter messages (tweets) containing medication mentions. Identifying personal mentions of COVID19 symptoms requires distinguishing personal mentions from other mentions such as symptoms reported by others and references to news articles or other sources. In this article, we describe our submission to Task 6 of the Social Media Mining for Health Applications (SMM4H) Shared Task 2021. This task challenged participants to classify tweets where the target classes are:(1) self-reports,(2) non-personal reports, and (3) literature/news mentions. Our system used a handcrafted preprocessing and word embeddings from BERT encoder model. We achieved an F1 score of 93%</abstract>
<identifier type="citekey">roychoudhury-naskar-2021-fine</identifier>
<identifier type="doi">10.18653/v1/2021.smm4h-1.30</identifier>
<location>
<url>https://aclanthology.org/2021.smm4h-1.30</url>
</location>
<part>
<date>2021-06</date>
<extent unit="page">
<start>138</start>
<end>140</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Fine-tuning BERT to classify COVID19 tweets containing symptoms
%A Roychoudhury, Rajarshi
%A Naskar, Sudip
%Y Magge, Arjun
%Y Klein, Ari
%Y Miranda-Escalada, Antonio
%Y Al-garadi, Mohammed Ali
%Y Alimova, Ilseyar
%Y Miftahutdinov, Zulfat
%Y Farre-Maduell, Eulalia
%Y Lopez, Salvador Lima
%Y Flores, Ivan
%Y O’Connor, Karen
%Y Weissenbacher, Davy
%Y Tutubalina, Elena
%Y Sarker, Abeed
%Y Banda, Juan M.
%Y Krallinger, Martin
%Y Gonzalez-Hernandez, Graciela
%S Proceedings of the Sixth Social Media Mining for Health (#SMM4H) Workshop and Shared Task
%D 2021
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F roychoudhury-naskar-2021-fine
%X Twitter is a valuable source of patient-generated data that has been used in various population health studies. The first step in many of these studies is to identify and capture Twitter messages (tweets) containing medication mentions. Identifying personal mentions of COVID19 symptoms requires distinguishing personal mentions from other mentions such as symptoms reported by others and references to news articles or other sources. In this article, we describe our submission to Task 6 of the Social Media Mining for Health Applications (SMM4H) Shared Task 2021. This task challenged participants to classify tweets where the target classes are:(1) self-reports,(2) non-personal reports, and (3) literature/news mentions. Our system used a handcrafted preprocessing and word embeddings from BERT encoder model. We achieved an F1 score of 93%
%R 10.18653/v1/2021.smm4h-1.30
%U https://aclanthology.org/2021.smm4h-1.30
%U https://doi.org/10.18653/v1/2021.smm4h-1.30
%P 138-140
Markdown (Informal)
[Fine-tuning BERT to classify COVID19 tweets containing symptoms](https://aclanthology.org/2021.smm4h-1.30) (Roychoudhury & Naskar, SMM4H 2021)
ACL