@inproceedings{whang-vosoughi-2020-dartmouth,
title = "{D}artmouth {CS} at {WNUT}-2020 Task 2: Informative {COVID}-19 Tweet Classification Using {BERT}",
author = "Whang, Dylan and
Vosoughi, Soroush",
editor = "Xu, Wei and
Ritter, Alan and
Baldwin, Tim and
Rahimi, Afshin",
booktitle = "Proceedings of the Sixth Workshop on Noisy User-generated Text (W-NUT 2020)",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.wnut-1.72",
doi = "10.18653/v1/2020.wnut-1.72",
pages = "480--484",
abstract = "We describe the systems developed for the WNUT-2020 shared task 2, identification of informative COVID-19 English Tweets. BERT is a highly performant model for Natural Language Processing tasks. We increased BERT{'}s performance in this classification task by fine-tuning BERT and concatenating its embeddings with Tweet-specific features and training a Support Vector Machine (SVM) for classification (henceforth called BERT+). We compared its performance to a suite of machine learning models. We used a Twitter specific data cleaning pipeline and word-level TF-IDF to extract features for the non-BERT models. BERT+ was the top performing model with an F1-score of 0.8713.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="whang-vosoughi-2020-dartmouth">
<titleInfo>
<title>Dartmouth CS at WNUT-2020 Task 2: Informative COVID-19 Tweet Classification Using BERT</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dylan</namePart>
<namePart type="family">Whang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Soroush</namePart>
<namePart type="family">Vosoughi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Sixth Workshop on Noisy User-generated Text (W-NUT 2020)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alan</namePart>
<namePart type="family">Ritter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tim</namePart>
<namePart type="family">Baldwin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Afshin</namePart>
<namePart type="family">Rahimi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We describe the systems developed for the WNUT-2020 shared task 2, identification of informative COVID-19 English Tweets. BERT is a highly performant model for Natural Language Processing tasks. We increased BERT’s performance in this classification task by fine-tuning BERT and concatenating its embeddings with Tweet-specific features and training a Support Vector Machine (SVM) for classification (henceforth called BERT+). We compared its performance to a suite of machine learning models. We used a Twitter specific data cleaning pipeline and word-level TF-IDF to extract features for the non-BERT models. BERT+ was the top performing model with an F1-score of 0.8713.</abstract>
<identifier type="citekey">whang-vosoughi-2020-dartmouth</identifier>
<identifier type="doi">10.18653/v1/2020.wnut-1.72</identifier>
<location>
<url>https://aclanthology.org/2020.wnut-1.72</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>480</start>
<end>484</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Dartmouth CS at WNUT-2020 Task 2: Informative COVID-19 Tweet Classification Using BERT
%A Whang, Dylan
%A Vosoughi, Soroush
%Y Xu, Wei
%Y Ritter, Alan
%Y Baldwin, Tim
%Y Rahimi, Afshin
%S Proceedings of the Sixth Workshop on Noisy User-generated Text (W-NUT 2020)
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F whang-vosoughi-2020-dartmouth
%X We describe the systems developed for the WNUT-2020 shared task 2, identification of informative COVID-19 English Tweets. BERT is a highly performant model for Natural Language Processing tasks. We increased BERT’s performance in this classification task by fine-tuning BERT and concatenating its embeddings with Tweet-specific features and training a Support Vector Machine (SVM) for classification (henceforth called BERT+). We compared its performance to a suite of machine learning models. We used a Twitter specific data cleaning pipeline and word-level TF-IDF to extract features for the non-BERT models. BERT+ was the top performing model with an F1-score of 0.8713.
%R 10.18653/v1/2020.wnut-1.72
%U https://aclanthology.org/2020.wnut-1.72
%U https://doi.org/10.18653/v1/2020.wnut-1.72
%P 480-484
Markdown (Informal)
[Dartmouth CS at WNUT-2020 Task 2: Informative COVID-19 Tweet Classification Using BERT](https://aclanthology.org/2020.wnut-1.72) (Whang & Vosoughi, WNUT 2020)
ACL