@inproceedings{valizadeh-etal-2023-clued,
title = "What Clued the {AI} Doctor In? On the Influence of Data Source and Quality for Transformer-Based Medical Self-Disclosure Detection",
author = "Valizadeh, Mina and
Qian, Xing and
Ranjbar-Noiey, Pardis and
Caragea, Cornelia and
Parde, Natalie",
editor = "Vlachos, Andreas and
Augenstein, Isabelle",
booktitle = "Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics",
month = may,
year = "2023",
address = "Dubrovnik, Croatia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.eacl-main.86",
doi = "10.18653/v1/2023.eacl-main.86",
pages = "1201--1216",
abstract = "Recognizing medical self-disclosure is important in many healthcare contexts, but it has been under-explored by the NLP community. We conduct a three-pronged investigation of this task. We (1) manually expand and refine the only existing medical self-disclosure corpus, resulting in a new, publicly available dataset of 3,919 social media posts with clinically validated labels and high compatibility with the existing task-specific protocol. We also (2) study the merits of pretraining task domain and text style by comparing Transformer-based models for this task, pretrained from general, medical, and social media sources. Our BERTweet condition outperforms the existing state of the art for this task by a relative F1 score increase of 16.73{\%}. Finally, we (3) compare data augmentation techniques for this task, to assess the extent to which medical self-disclosure data may be further synthetically expanded. We discover that this task poses many challenges for data augmentation techniques, and we provide an in-depth analysis of identified trends.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="valizadeh-etal-2023-clued">
<titleInfo>
<title>What Clued the AI Doctor In? On the Influence of Data Source and Quality for Transformer-Based Medical Self-Disclosure Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mina</namePart>
<namePart type="family">Valizadeh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xing</namePart>
<namePart type="family">Qian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pardis</namePart>
<namePart type="family">Ranjbar-Noiey</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cornelia</namePart>
<namePart type="family">Caragea</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Natalie</namePart>
<namePart type="family">Parde</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Andreas</namePart>
<namePart type="family">Vlachos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Isabelle</namePart>
<namePart type="family">Augenstein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dubrovnik, Croatia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Recognizing medical self-disclosure is important in many healthcare contexts, but it has been under-explored by the NLP community. We conduct a three-pronged investigation of this task. We (1) manually expand and refine the only existing medical self-disclosure corpus, resulting in a new, publicly available dataset of 3,919 social media posts with clinically validated labels and high compatibility with the existing task-specific protocol. We also (2) study the merits of pretraining task domain and text style by comparing Transformer-based models for this task, pretrained from general, medical, and social media sources. Our BERTweet condition outperforms the existing state of the art for this task by a relative F1 score increase of 16.73%. Finally, we (3) compare data augmentation techniques for this task, to assess the extent to which medical self-disclosure data may be further synthetically expanded. We discover that this task poses many challenges for data augmentation techniques, and we provide an in-depth analysis of identified trends.</abstract>
<identifier type="citekey">valizadeh-etal-2023-clued</identifier>
<identifier type="doi">10.18653/v1/2023.eacl-main.86</identifier>
<location>
<url>https://aclanthology.org/2023.eacl-main.86</url>
</location>
<part>
<date>2023-05</date>
<extent unit="page">
<start>1201</start>
<end>1216</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T What Clued the AI Doctor In? On the Influence of Data Source and Quality for Transformer-Based Medical Self-Disclosure Detection
%A Valizadeh, Mina
%A Qian, Xing
%A Ranjbar-Noiey, Pardis
%A Caragea, Cornelia
%A Parde, Natalie
%Y Vlachos, Andreas
%Y Augenstein, Isabelle
%S Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics
%D 2023
%8 May
%I Association for Computational Linguistics
%C Dubrovnik, Croatia
%F valizadeh-etal-2023-clued
%X Recognizing medical self-disclosure is important in many healthcare contexts, but it has been under-explored by the NLP community. We conduct a three-pronged investigation of this task. We (1) manually expand and refine the only existing medical self-disclosure corpus, resulting in a new, publicly available dataset of 3,919 social media posts with clinically validated labels and high compatibility with the existing task-specific protocol. We also (2) study the merits of pretraining task domain and text style by comparing Transformer-based models for this task, pretrained from general, medical, and social media sources. Our BERTweet condition outperforms the existing state of the art for this task by a relative F1 score increase of 16.73%. Finally, we (3) compare data augmentation techniques for this task, to assess the extent to which medical self-disclosure data may be further synthetically expanded. We discover that this task poses many challenges for data augmentation techniques, and we provide an in-depth analysis of identified trends.
%R 10.18653/v1/2023.eacl-main.86
%U https://aclanthology.org/2023.eacl-main.86
%U https://doi.org/10.18653/v1/2023.eacl-main.86
%P 1201-1216
Markdown (Informal)
[What Clued the AI Doctor In? On the Influence of Data Source and Quality for Transformer-Based Medical Self-Disclosure Detection](https://aclanthology.org/2023.eacl-main.86) (Valizadeh et al., EACL 2023)
ACL