@inproceedings{wuhrl-klinger-2022-recovering,
title = "Recovering Patient Journeys: A Corpus of Biomedical Entities and Relations on {T}witter ({BEAR})",
author = {W{\"u}hrl, Amelie and
Klinger, Roman},
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Thirteenth Language Resources and Evaluation Conference",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.lrec-1.472",
pages = "4439--4450",
abstract = "Text mining and information extraction for the medical domain has focused on scientific text generated by researchers. However, their access to individual patient experiences or patient-doctor interactions is limited. On social media, doctors, patients and their relatives also discuss medical information. Individual information provided by laypeople complements the knowledge available in scientific text. It reflects the patient{'}s journey making the value of this type of data twofold: It offers direct access to people{'}s perspectives, and it might cover information that is not available elsewhere, including self-treatment or self-diagnose. Named entity recognition and relation extraction are methods to structure information that is available in unstructured text. However, existing medical social media corpora focused on a comparably small set of entities and relations. In contrast, we provide rich annotation layers to model patients{'} experiences in detail. The corpus consists of medical tweets annotated with a fine-grained set of medical entities and relations between them, namely 14 entity (incl. environmental factors, diagnostics, biochemical processes, patients{'} quality-of-life descriptions, pathogens, medical conditions, and treatments) and 20 relation classes (incl. prevents, influences, interactions, causes). The dataset consists of 2,100 tweets with approx. 6,000 entities and 2,200 relations.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wuhrl-klinger-2022-recovering">
<titleInfo>
<title>Recovering Patient Journeys: A Corpus of Biomedical Entities and Relations on Twitter (BEAR)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Amelie</namePart>
<namePart type="family">Wührl</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roman</namePart>
<namePart type="family">Klinger</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Thirteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Cieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hélène</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Text mining and information extraction for the medical domain has focused on scientific text generated by researchers. However, their access to individual patient experiences or patient-doctor interactions is limited. On social media, doctors, patients and their relatives also discuss medical information. Individual information provided by laypeople complements the knowledge available in scientific text. It reflects the patient’s journey making the value of this type of data twofold: It offers direct access to people’s perspectives, and it might cover information that is not available elsewhere, including self-treatment or self-diagnose. Named entity recognition and relation extraction are methods to structure information that is available in unstructured text. However, existing medical social media corpora focused on a comparably small set of entities and relations. In contrast, we provide rich annotation layers to model patients’ experiences in detail. The corpus consists of medical tweets annotated with a fine-grained set of medical entities and relations between them, namely 14 entity (incl. environmental factors, diagnostics, biochemical processes, patients’ quality-of-life descriptions, pathogens, medical conditions, and treatments) and 20 relation classes (incl. prevents, influences, interactions, causes). The dataset consists of 2,100 tweets with approx. 6,000 entities and 2,200 relations.</abstract>
<identifier type="citekey">wuhrl-klinger-2022-recovering</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.472</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>4439</start>
<end>4450</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Recovering Patient Journeys: A Corpus of Biomedical Entities and Relations on Twitter (BEAR)
%A Wührl, Amelie
%A Klinger, Roman
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Thirteenth Language Resources and Evaluation Conference
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F wuhrl-klinger-2022-recovering
%X Text mining and information extraction for the medical domain has focused on scientific text generated by researchers. However, their access to individual patient experiences or patient-doctor interactions is limited. On social media, doctors, patients and their relatives also discuss medical information. Individual information provided by laypeople complements the knowledge available in scientific text. It reflects the patient’s journey making the value of this type of data twofold: It offers direct access to people’s perspectives, and it might cover information that is not available elsewhere, including self-treatment or self-diagnose. Named entity recognition and relation extraction are methods to structure information that is available in unstructured text. However, existing medical social media corpora focused on a comparably small set of entities and relations. In contrast, we provide rich annotation layers to model patients’ experiences in detail. The corpus consists of medical tweets annotated with a fine-grained set of medical entities and relations between them, namely 14 entity (incl. environmental factors, diagnostics, biochemical processes, patients’ quality-of-life descriptions, pathogens, medical conditions, and treatments) and 20 relation classes (incl. prevents, influences, interactions, causes). The dataset consists of 2,100 tweets with approx. 6,000 entities and 2,200 relations.
%U https://aclanthology.org/2022.lrec-1.472
%P 4439-4450
Markdown (Informal)
[Recovering Patient Journeys: A Corpus of Biomedical Entities and Relations on Twitter (BEAR)](https://aclanthology.org/2022.lrec-1.472) (Wührl & Klinger, LREC 2022)
ACL