@inproceedings{morlane-hondere-etal-2016-identification,
title = "Identification of Drug-Related Medical Conditions in Social Media",
author = "Morlane-Hond{\`e}re, Fran{\c{c}}ois and
Grouin, Cyril and
Zweigenbaum, Pierre",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Goggi, Sara and
Grobelnik, Marko and
Maegaard, Bente and
Mariani, Joseph and
Mazo, Helene and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Tenth International Conference on Language Resources and Evaluation ({LREC}'16)",
month = may,
year = "2016",
address = "Portoro{\v{z}}, Slovenia",
publisher = "European Language Resources Association (ELRA)",
url = "https://aclanthology.org/L16-1320",
pages = "2022--2028",
abstract = "Monitoring social media has been shown to be an interesting approach for the early detection of drug adverse effects. In this paper, we describe a system which extracts medical entities in French drug reviews written by users. We focus on the identification of medical conditions, which is based on the concept of post-coordination: we first extract minimal medical-related entities (pain, stomach) then we combine them to identify complex ones (It was the worst [pain I ever felt in my stomach]). These two steps are respectively performed by two classifiers, the first being based on Conditional Random Fields and the second one on Support Vector Machines. The overall results of the minimal entity classifier are the following: P=0.926; R=0.849; F1=0.886. A thourough analysis of the feature set shows that, when combined with word lemmas, clusters generated by word2vec are the most valuable features. When trained on the output of the first classifier, the second classifier{'}s performances are the following: p=0.683;r=0.956;f1=0.797. The addition of post-processing rules did not add any significant global improvement but was found to modify the precision/recall ratio.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="morlane-hondere-etal-2016-identification">
<titleInfo>
<title>Identification of Drug-Related Medical Conditions in Social Media</title>
</titleInfo>
<name type="personal">
<namePart type="given">François</namePart>
<namePart type="family">Morlane-Hondère</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cyril</namePart>
<namePart type="family">Grouin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pierre</namePart>
<namePart type="family">Zweigenbaum</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2016-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)</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">Khalid</namePart>
<namePart type="family">Choukri</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">Marko</namePart>
<namePart type="family">Grobelnik</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">Helene</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asuncion</namePart>
<namePart type="family">Moreno</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 (ELRA)</publisher>
<place>
<placeTerm type="text">Portorož, Slovenia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Monitoring social media has been shown to be an interesting approach for the early detection of drug adverse effects. In this paper, we describe a system which extracts medical entities in French drug reviews written by users. We focus on the identification of medical conditions, which is based on the concept of post-coordination: we first extract minimal medical-related entities (pain, stomach) then we combine them to identify complex ones (It was the worst [pain I ever felt in my stomach]). These two steps are respectively performed by two classifiers, the first being based on Conditional Random Fields and the second one on Support Vector Machines. The overall results of the minimal entity classifier are the following: P=0.926; R=0.849; F1=0.886. A thourough analysis of the feature set shows that, when combined with word lemmas, clusters generated by word2vec are the most valuable features. When trained on the output of the first classifier, the second classifier’s performances are the following: p=0.683;r=0.956;f1=0.797. The addition of post-processing rules did not add any significant global improvement but was found to modify the precision/recall ratio.</abstract>
<identifier type="citekey">morlane-hondere-etal-2016-identification</identifier>
<location>
<url>https://aclanthology.org/L16-1320</url>
</location>
<part>
<date>2016-05</date>
<extent unit="page">
<start>2022</start>
<end>2028</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Identification of Drug-Related Medical Conditions in Social Media
%A Morlane-Hondère, François
%A Grouin, Cyril
%A Zweigenbaum, Pierre
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Grobelnik, Marko
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Helene
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)
%D 2016
%8 May
%I European Language Resources Association (ELRA)
%C Portorož, Slovenia
%F morlane-hondere-etal-2016-identification
%X Monitoring social media has been shown to be an interesting approach for the early detection of drug adverse effects. In this paper, we describe a system which extracts medical entities in French drug reviews written by users. We focus on the identification of medical conditions, which is based on the concept of post-coordination: we first extract minimal medical-related entities (pain, stomach) then we combine them to identify complex ones (It was the worst [pain I ever felt in my stomach]). These two steps are respectively performed by two classifiers, the first being based on Conditional Random Fields and the second one on Support Vector Machines. The overall results of the minimal entity classifier are the following: P=0.926; R=0.849; F1=0.886. A thourough analysis of the feature set shows that, when combined with word lemmas, clusters generated by word2vec are the most valuable features. When trained on the output of the first classifier, the second classifier’s performances are the following: p=0.683;r=0.956;f1=0.797. The addition of post-processing rules did not add any significant global improvement but was found to modify the precision/recall ratio.
%U https://aclanthology.org/L16-1320
%P 2022-2028
Markdown (Informal)
[Identification of Drug-Related Medical Conditions in Social Media](https://aclanthology.org/L16-1320) (Morlane-Hondère et al., LREC 2016)
ACL