@inproceedings{rajwal-etal-2024-unveiling,
title = "Unveiling Voices: Identification of Concerns in a Social Media Breast Cancer Cohort via Natural Language Processing",
author = "Rajwal, Swati and
Pandey, Avinash Kumar and
Han, Zhishuo and
Sarker, Abeed",
editor = "Demner-Fushman, Dina and
Ananiadou, Sophia and
Thompson, Paul and
Ondov, Brian",
booktitle = "Proceedings of the First Workshop on Patient-Oriented Language Processing (CL4Health) @ LREC-COLING 2024",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.cl4health-1.32",
pages = "264--270",
abstract = "We leveraged a dataset of ∼1.5 million Twitter (now X) posts to develop a framework for analyzing breast cancer (BC) patients{'} concerns and possible reasons for treatment discontinuation. Our primary objectives were threefold: (1) to curate and collect data from a BC cohort; (2) to identify topics related to uncertainty/concerns in BC-related posts; and (3) to conduct a sentiment intensity analysis of posts to identify and analyze negatively polarized posts. RoBERTa outperformed other models with a micro-averaged F1 score of 0.894 and a macro-averaged F1 score of 0.853 for (1). For (2), we used GPT-4 and BERTopic, and qualitatively analyzed posts under relevant topics. For (3), sentiment intensity analysis of posts followed by qualitative analyses shed light on potential reasons behind treatment discontinuation. Our work demonstrates the utility of social media mining to discover BC patient concerns. Information derived from the cohort data may help design strategies in the future for increasing treatment compliance.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rajwal-etal-2024-unveiling">
<titleInfo>
<title>Unveiling Voices: Identification of Concerns in a Social Media Breast Cancer Cohort via Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Swati</namePart>
<namePart type="family">Rajwal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Avinash</namePart>
<namePart type="given">Kumar</namePart>
<namePart type="family">Pandey</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhishuo</namePart>
<namePart type="family">Han</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abeed</namePart>
<namePart type="family">Sarker</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the First Workshop on Patient-Oriented Language Processing (CL4Health) @ LREC-COLING 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dina</namePart>
<namePart type="family">Demner-Fushman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sophia</namePart>
<namePart type="family">Ananiadou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paul</namePart>
<namePart type="family">Thompson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Brian</namePart>
<namePart type="family">Ondov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We leveraged a dataset of ∼1.5 million Twitter (now X) posts to develop a framework for analyzing breast cancer (BC) patients’ concerns and possible reasons for treatment discontinuation. Our primary objectives were threefold: (1) to curate and collect data from a BC cohort; (2) to identify topics related to uncertainty/concerns in BC-related posts; and (3) to conduct a sentiment intensity analysis of posts to identify and analyze negatively polarized posts. RoBERTa outperformed other models with a micro-averaged F1 score of 0.894 and a macro-averaged F1 score of 0.853 for (1). For (2), we used GPT-4 and BERTopic, and qualitatively analyzed posts under relevant topics. For (3), sentiment intensity analysis of posts followed by qualitative analyses shed light on potential reasons behind treatment discontinuation. Our work demonstrates the utility of social media mining to discover BC patient concerns. Information derived from the cohort data may help design strategies in the future for increasing treatment compliance.</abstract>
<identifier type="citekey">rajwal-etal-2024-unveiling</identifier>
<location>
<url>https://aclanthology.org/2024.cl4health-1.32</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>264</start>
<end>270</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Unveiling Voices: Identification of Concerns in a Social Media Breast Cancer Cohort via Natural Language Processing
%A Rajwal, Swati
%A Pandey, Avinash Kumar
%A Han, Zhishuo
%A Sarker, Abeed
%Y Demner-Fushman, Dina
%Y Ananiadou, Sophia
%Y Thompson, Paul
%Y Ondov, Brian
%S Proceedings of the First Workshop on Patient-Oriented Language Processing (CL4Health) @ LREC-COLING 2024
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F rajwal-etal-2024-unveiling
%X We leveraged a dataset of ∼1.5 million Twitter (now X) posts to develop a framework for analyzing breast cancer (BC) patients’ concerns and possible reasons for treatment discontinuation. Our primary objectives were threefold: (1) to curate and collect data from a BC cohort; (2) to identify topics related to uncertainty/concerns in BC-related posts; and (3) to conduct a sentiment intensity analysis of posts to identify and analyze negatively polarized posts. RoBERTa outperformed other models with a micro-averaged F1 score of 0.894 and a macro-averaged F1 score of 0.853 for (1). For (2), we used GPT-4 and BERTopic, and qualitatively analyzed posts under relevant topics. For (3), sentiment intensity analysis of posts followed by qualitative analyses shed light on potential reasons behind treatment discontinuation. Our work demonstrates the utility of social media mining to discover BC patient concerns. Information derived from the cohort data may help design strategies in the future for increasing treatment compliance.
%U https://aclanthology.org/2024.cl4health-1.32
%P 264-270
Markdown (Informal)
[Unveiling Voices: Identification of Concerns in a Social Media Breast Cancer Cohort via Natural Language Processing](https://aclanthology.org/2024.cl4health-1.32) (Rajwal et al., CL4Health-WS 2024)
ACL