@inproceedings{gasco-sanchez-etal-2022-socialdisner,
title = "The {S}ocial{D}is{NER} shared task on detection of disease mentions in health-relevant content from social media: methods, evaluation, guidelines and corpora",
author = "Gasco S{\'a}nchez, Luis and
Estrada Zavala, Darryl and
Farr{\'e}-Maduell, Eul{\`a}lia and
Lima-L{\'o}pez, Salvador and
Miranda-Escalada, Antonio and
Krallinger, Martin",
editor = "Gonzalez-Hernandez, Graciela and
Weissenbacher, Davy",
booktitle = "Proceedings of The Seventh Workshop on Social Media Mining for Health Applications, Workshop {\&} Shared Task",
month = oct,
year = "2022",
address = "Gyeongju, Republic of Korea",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.smm4h-1.48",
pages = "182--189",
abstract = "There is a pressing need to exploit health-related content from social media, a global source of data where key health information is posted directly by citizens, patients and other healthcare stakeholders. Use cases of disease related social media mining include disease outbreak/surveillance, mental health and pharmacovigilance. Current efforts address the exploitation of social media beyond English. The SocialDisNER task, organized as part of the SMM4H 2022 initiative, has applied the LINKAGE methodology to select and annotate a Gold Standard corpus of 9,500 tweets in Spanish enriched with disease mentions generated by patients and medical professionals. As a complementary resource for teams participating in the SocialDisNER track, we have also created a large-scale corpus of 85,000 tweets, where in addition to disease mentions, other medical entities of relevance (e.g., medications, symptoms and procedures, among others) have been automatically labelled. Using these large-scale datasets, co-mention networks or knowledge graphs were released for each entity pair type. Out of the 47 teams registered for the task, 17 teams uploaded a total of 32 runs. The top-performing team achieved a very competitive 0.891 f-score, with a system trained following a continue pre-training strategy. We anticipate that the corpus and systems resulting from the SocialDisNER track might further foster health related text mining of social media content in Spanish and inspire disease detection strategies in other languages.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gasco-sanchez-etal-2022-socialdisner">
<titleInfo>
<title>The SocialDisNER shared task on detection of disease mentions in health-relevant content from social media: methods, evaluation, guidelines and corpora</title>
</titleInfo>
<name type="personal">
<namePart type="given">Luis</namePart>
<namePart type="family">Gasco Sánchez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Darryl</namePart>
<namePart type="family">Estrada Zavala</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eulàlia</namePart>
<namePart type="family">Farré-Maduell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Salvador</namePart>
<namePart type="family">Lima-López</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Miranda-Escalada</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Martin</namePart>
<namePart type="family">Krallinger</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 Seventh Workshop on Social Media Mining for Health Applications, Workshop & Shared Task</title>
</titleInfo>
<name type="personal">
<namePart type="given">Graciela</namePart>
<namePart type="family">Gonzalez-Hernandez</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>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Gyeongju, Republic of Korea</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>There is a pressing need to exploit health-related content from social media, a global source of data where key health information is posted directly by citizens, patients and other healthcare stakeholders. Use cases of disease related social media mining include disease outbreak/surveillance, mental health and pharmacovigilance. Current efforts address the exploitation of social media beyond English. The SocialDisNER task, organized as part of the SMM4H 2022 initiative, has applied the LINKAGE methodology to select and annotate a Gold Standard corpus of 9,500 tweets in Spanish enriched with disease mentions generated by patients and medical professionals. As a complementary resource for teams participating in the SocialDisNER track, we have also created a large-scale corpus of 85,000 tweets, where in addition to disease mentions, other medical entities of relevance (e.g., medications, symptoms and procedures, among others) have been automatically labelled. Using these large-scale datasets, co-mention networks or knowledge graphs were released for each entity pair type. Out of the 47 teams registered for the task, 17 teams uploaded a total of 32 runs. The top-performing team achieved a very competitive 0.891 f-score, with a system trained following a continue pre-training strategy. We anticipate that the corpus and systems resulting from the SocialDisNER track might further foster health related text mining of social media content in Spanish and inspire disease detection strategies in other languages.</abstract>
<identifier type="citekey">gasco-sanchez-etal-2022-socialdisner</identifier>
<location>
<url>https://aclanthology.org/2022.smm4h-1.48</url>
</location>
<part>
<date>2022-10</date>
<extent unit="page">
<start>182</start>
<end>189</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The SocialDisNER shared task on detection of disease mentions in health-relevant content from social media: methods, evaluation, guidelines and corpora
%A Gasco Sánchez, Luis
%A Estrada Zavala, Darryl
%A Farré-Maduell, Eulàlia
%A Lima-López, Salvador
%A Miranda-Escalada, Antonio
%A Krallinger, Martin
%Y Gonzalez-Hernandez, Graciela
%Y Weissenbacher, Davy
%S Proceedings of The Seventh Workshop on Social Media Mining for Health Applications, Workshop & Shared Task
%D 2022
%8 October
%I Association for Computational Linguistics
%C Gyeongju, Republic of Korea
%F gasco-sanchez-etal-2022-socialdisner
%X There is a pressing need to exploit health-related content from social media, a global source of data where key health information is posted directly by citizens, patients and other healthcare stakeholders. Use cases of disease related social media mining include disease outbreak/surveillance, mental health and pharmacovigilance. Current efforts address the exploitation of social media beyond English. The SocialDisNER task, organized as part of the SMM4H 2022 initiative, has applied the LINKAGE methodology to select and annotate a Gold Standard corpus of 9,500 tweets in Spanish enriched with disease mentions generated by patients and medical professionals. As a complementary resource for teams participating in the SocialDisNER track, we have also created a large-scale corpus of 85,000 tweets, where in addition to disease mentions, other medical entities of relevance (e.g., medications, symptoms and procedures, among others) have been automatically labelled. Using these large-scale datasets, co-mention networks or knowledge graphs were released for each entity pair type. Out of the 47 teams registered for the task, 17 teams uploaded a total of 32 runs. The top-performing team achieved a very competitive 0.891 f-score, with a system trained following a continue pre-training strategy. We anticipate that the corpus and systems resulting from the SocialDisNER track might further foster health related text mining of social media content in Spanish and inspire disease detection strategies in other languages.
%U https://aclanthology.org/2022.smm4h-1.48
%P 182-189
Markdown (Informal)
[The SocialDisNER shared task on detection of disease mentions in health-relevant content from social media: methods, evaluation, guidelines and corpora](https://aclanthology.org/2022.smm4h-1.48) (Gasco Sánchez et al., SMM4H 2022)
ACL
- Luis Gasco Sánchez, Darryl Estrada Zavala, Eulàlia Farré-Maduell, Salvador Lima-López, Antonio Miranda-Escalada, and Martin Krallinger. 2022. The SocialDisNER shared task on detection of disease mentions in health-relevant content from social media: methods, evaluation, guidelines and corpora. In Proceedings of The Seventh Workshop on Social Media Mining for Health Applications, Workshop & Shared Task, pages 182–189, Gyeongju, Republic of Korea. Association for Computational Linguistics.