@inproceedings{zong-etal-2022-extracting,
title = "Extracting a Knowledge Base of {COVID}-19 Events from Social Media",
author = "Zong, Shi and
Baheti, Ashutosh and
Xu, Wei and
Ritter, Alan",
booktitle = "Proceedings of the 29th International Conference on Computational Linguistics",
month = oct,
year = "2022",
address = "Gyeongju, Republic of Korea",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2022.coling-1.335",
pages = "3810--3823",
abstract = "We present a manually annotated corpus of 10,000 tweets containing public reports of five COVID-19 events, including positive and negative tests, deaths, denied access to testing, claimed cures and preventions. We designed slot-filling questions for each event type and annotated a total of 28 fine-grained slots, such as the location of events, recent travel, and close contacts. We show that our corpus can support fine-tuning BERT-based classifiers to automatically extract publicly reported events, which can be further collected for building a knowledge base. Our knowledge base is constructed over Twitter data covering two years and currently covers over 4.2M events. It can answer complex queries with high precision, such as {``}Which organizations have employees that tested positive in Philadelphia?{''} We believe our proposed methodology could be quickly applied to develop knowledge bases for new domains in response to an emerging crisis, including natural disasters or future disease outbreaks.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zong-etal-2022-extracting">
<titleInfo>
<title>Extracting a Knowledge Base of COVID-19 Events from Social Media</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shi</namePart>
<namePart type="family">Zong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ashutosh</namePart>
<namePart type="family">Baheti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alan</namePart>
<namePart type="family">Ritter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 29th International Conference on Computational Linguistics</title>
</titleInfo>
<originInfo>
<publisher>International Committee on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Gyeongju, Republic of Korea</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present a manually annotated corpus of 10,000 tweets containing public reports of five COVID-19 events, including positive and negative tests, deaths, denied access to testing, claimed cures and preventions. We designed slot-filling questions for each event type and annotated a total of 28 fine-grained slots, such as the location of events, recent travel, and close contacts. We show that our corpus can support fine-tuning BERT-based classifiers to automatically extract publicly reported events, which can be further collected for building a knowledge base. Our knowledge base is constructed over Twitter data covering two years and currently covers over 4.2M events. It can answer complex queries with high precision, such as “Which organizations have employees that tested positive in Philadelphia?” We believe our proposed methodology could be quickly applied to develop knowledge bases for new domains in response to an emerging crisis, including natural disasters or future disease outbreaks.</abstract>
<identifier type="citekey">zong-etal-2022-extracting</identifier>
<location>
<url>https://aclanthology.org/2022.coling-1.335</url>
</location>
<part>
<date>2022-10</date>
<extent unit="page">
<start>3810</start>
<end>3823</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Extracting a Knowledge Base of COVID-19 Events from Social Media
%A Zong, Shi
%A Baheti, Ashutosh
%A Xu, Wei
%A Ritter, Alan
%S Proceedings of the 29th International Conference on Computational Linguistics
%D 2022
%8 October
%I International Committee on Computational Linguistics
%C Gyeongju, Republic of Korea
%F zong-etal-2022-extracting
%X We present a manually annotated corpus of 10,000 tweets containing public reports of five COVID-19 events, including positive and negative tests, deaths, denied access to testing, claimed cures and preventions. We designed slot-filling questions for each event type and annotated a total of 28 fine-grained slots, such as the location of events, recent travel, and close contacts. We show that our corpus can support fine-tuning BERT-based classifiers to automatically extract publicly reported events, which can be further collected for building a knowledge base. Our knowledge base is constructed over Twitter data covering two years and currently covers over 4.2M events. It can answer complex queries with high precision, such as “Which organizations have employees that tested positive in Philadelphia?” We believe our proposed methodology could be quickly applied to develop knowledge bases for new domains in response to an emerging crisis, including natural disasters or future disease outbreaks.
%U https://aclanthology.org/2022.coling-1.335
%P 3810-3823
Markdown (Informal)
[Extracting a Knowledge Base of COVID-19 Events from Social Media](https://aclanthology.org/2022.coling-1.335) (Zong et al., COLING 2022)
ACL