@inproceedings{wasi-rahman-2024-dilab,
title = "{DILAB} at {\#}{SMM}4{H} 2024: {R}o{BERT}a Ensemble for Identifying Children{'}s Medical Disorders in {E}nglish Tweets",
author = "Wasi, Azmine Toushik and
Rahman, Sheikh",
editor = "Xu, Dongfang and
Gonzalez-Hernandez, Graciela",
booktitle = "Proceedings of The 9th Social Media Mining for Health Research and Applications (SMM4H 2024) Workshop and Shared Tasks",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.smm4h-1.3",
pages = "10--12",
abstract = "This paper details our system developed for the 9th Social Media Mining for Health Research and Applications Workshop (SMM4H 2024), addressing Task 5 focused on binary classification of English tweets reporting children{'}s medical disorders. Our objective was to enhance the detection of tweets related to children{'}s medical issues. To do this, we use various pre-trained language models, like RoBERTa and BERT. We fine-tuned these models on the task-specific dataset, adjusting model layers and hyperparameters in an attempt to optimize performance. As we observe unstable fluctuations in performance metrics during training, we implement an ensemble approach that combines predictions from different learning epochs. Our model achieves promising results, with the best-performing configuration achieving F1 score of 93.8{\%} on the validation set and 89.8{\%} on the test set.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wasi-rahman-2024-dilab">
<titleInfo>
<title>DILAB at #SMM4H 2024: RoBERTa Ensemble for Identifying Children’s Medical Disorders in English Tweets</title>
</titleInfo>
<name type="personal">
<namePart type="given">Azmine</namePart>
<namePart type="given">Toushik</namePart>
<namePart type="family">Wasi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sheikh</namePart>
<namePart type="family">Rahman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of The 9th Social Media Mining for Health Research and Applications (SMM4H 2024) Workshop and Shared Tasks</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dongfang</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Graciela</namePart>
<namePart type="family">Gonzalez-Hernandez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper details our system developed for the 9th Social Media Mining for Health Research and Applications Workshop (SMM4H 2024), addressing Task 5 focused on binary classification of English tweets reporting children’s medical disorders. Our objective was to enhance the detection of tweets related to children’s medical issues. To do this, we use various pre-trained language models, like RoBERTa and BERT. We fine-tuned these models on the task-specific dataset, adjusting model layers and hyperparameters in an attempt to optimize performance. As we observe unstable fluctuations in performance metrics during training, we implement an ensemble approach that combines predictions from different learning epochs. Our model achieves promising results, with the best-performing configuration achieving F1 score of 93.8% on the validation set and 89.8% on the test set.</abstract>
<identifier type="citekey">wasi-rahman-2024-dilab</identifier>
<location>
<url>https://aclanthology.org/2024.smm4h-1.3</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>10</start>
<end>12</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T DILAB at #SMM4H 2024: RoBERTa Ensemble for Identifying Children’s Medical Disorders in English Tweets
%A Wasi, Azmine Toushik
%A Rahman, Sheikh
%Y Xu, Dongfang
%Y Gonzalez-Hernandez, Graciela
%S Proceedings of The 9th Social Media Mining for Health Research and Applications (SMM4H 2024) Workshop and Shared Tasks
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F wasi-rahman-2024-dilab
%X This paper details our system developed for the 9th Social Media Mining for Health Research and Applications Workshop (SMM4H 2024), addressing Task 5 focused on binary classification of English tweets reporting children’s medical disorders. Our objective was to enhance the detection of tweets related to children’s medical issues. To do this, we use various pre-trained language models, like RoBERTa and BERT. We fine-tuned these models on the task-specific dataset, adjusting model layers and hyperparameters in an attempt to optimize performance. As we observe unstable fluctuations in performance metrics during training, we implement an ensemble approach that combines predictions from different learning epochs. Our model achieves promising results, with the best-performing configuration achieving F1 score of 93.8% on the validation set and 89.8% on the test set.
%U https://aclanthology.org/2024.smm4h-1.3
%P 10-12
Markdown (Informal)
[DILAB at #SMM4H 2024: RoBERTa Ensemble for Identifying Children’s Medical Disorders in English Tweets](https://aclanthology.org/2024.smm4h-1.3) (Wasi & Rahman, SMM4H-WS 2024)
ACL