@inproceedings{nishiyama-etal-2024-assessing,
title = "Assessing Authenticity and Anonymity of Synthetic User-generated Content in the Medical Domain",
author = "Nishiyama, Tomohiro and
Raithel, Lisa and
Roller, Roland and
Zweigenbaum, Pierre and
Aramaki, Eiji",
editor = {Volodina, Elena and
Alfter, David and
Dobnik, Simon and
Lindstr{\"o}m Tiedemann, Therese and
Mu{\~n}oz S{\'a}nchez, Ricardo and
Szawerna, Maria Irena and
Vu, Xuan-Son},
booktitle = "Proceedings of the Workshop on Computational Approaches to Language Data Pseudonymization (CALD-pseudo 2024)",
month = mar,
year = "2024",
address = "St. Julian{'}s, Malta",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.caldpseudo-1.2",
pages = "8--17",
abstract = "Since medical text cannot be shared easily due to privacy concerns, synthetic data bears much potential for natural language processing applications. In the context of social media and user-generated messages about drug intake and adverse drug effects, this work presents different methods to examine the authenticity of synthetic text. We conclude that the generated tweets are untraceable and show enough authenticity from the medical point of view to be used as a replacement for a real Twitter corpus. However, original data might still be the preferred choice as they contain much more diversity.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nishiyama-etal-2024-assessing">
<titleInfo>
<title>Assessing Authenticity and Anonymity of Synthetic User-generated Content in the Medical Domain</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tomohiro</namePart>
<namePart type="family">Nishiyama</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lisa</namePart>
<namePart type="family">Raithel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roland</namePart>
<namePart type="family">Roller</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>
<name type="personal">
<namePart type="given">Eiji</namePart>
<namePart type="family">Aramaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Workshop on Computational Approaches to Language Data Pseudonymization (CALD-pseudo 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Elena</namePart>
<namePart type="family">Volodina</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Alfter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Dobnik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Therese</namePart>
<namePart type="family">Lindström Tiedemann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ricardo</namePart>
<namePart type="family">Muñoz Sánchez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="given">Irena</namePart>
<namePart type="family">Szawerna</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuan-Son</namePart>
<namePart type="family">Vu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">St. Julian’s, Malta</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Since medical text cannot be shared easily due to privacy concerns, synthetic data bears much potential for natural language processing applications. In the context of social media and user-generated messages about drug intake and adverse drug effects, this work presents different methods to examine the authenticity of synthetic text. We conclude that the generated tweets are untraceable and show enough authenticity from the medical point of view to be used as a replacement for a real Twitter corpus. However, original data might still be the preferred choice as they contain much more diversity.</abstract>
<identifier type="citekey">nishiyama-etal-2024-assessing</identifier>
<location>
<url>https://aclanthology.org/2024.caldpseudo-1.2</url>
</location>
<part>
<date>2024-03</date>
<extent unit="page">
<start>8</start>
<end>17</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Assessing Authenticity and Anonymity of Synthetic User-generated Content in the Medical Domain
%A Nishiyama, Tomohiro
%A Raithel, Lisa
%A Roller, Roland
%A Zweigenbaum, Pierre
%A Aramaki, Eiji
%Y Volodina, Elena
%Y Alfter, David
%Y Dobnik, Simon
%Y Lindström Tiedemann, Therese
%Y Muñoz Sánchez, Ricardo
%Y Szawerna, Maria Irena
%Y Vu, Xuan-Son
%S Proceedings of the Workshop on Computational Approaches to Language Data Pseudonymization (CALD-pseudo 2024)
%D 2024
%8 March
%I Association for Computational Linguistics
%C St. Julian’s, Malta
%F nishiyama-etal-2024-assessing
%X Since medical text cannot be shared easily due to privacy concerns, synthetic data bears much potential for natural language processing applications. In the context of social media and user-generated messages about drug intake and adverse drug effects, this work presents different methods to examine the authenticity of synthetic text. We conclude that the generated tweets are untraceable and show enough authenticity from the medical point of view to be used as a replacement for a real Twitter corpus. However, original data might still be the preferred choice as they contain much more diversity.
%U https://aclanthology.org/2024.caldpseudo-1.2
%P 8-17
Markdown (Informal)
[Assessing Authenticity and Anonymity of Synthetic User-generated Content in the Medical Domain](https://aclanthology.org/2024.caldpseudo-1.2) (Nishiyama et al., CALD-pseudo-WS 2024)
ACL