@inproceedings{bansal-etal-2026-halelab,
title = "{HALEL}ab-{NITK} at {\#}{SMM}4{H}-{H}ea{RD}2026: Inclusion of Feature Engineering for Detection of Patient Metadata in {SARS}-{C}o{V}2 Sequencing Articles",
author = "Bansal, Aakarsh and
Srinivas, Abhishek and
Kamath S., Sowmya",
editor = "Lopez-Garcia, Guillermo and
Gonzalez-Hernandez, Graciela",
booktitle = "Proceedings of the 11th Social Media Mining for Health Research and Applications ({SMM}4{H}-{H}ea{RD} 2026) Workshop and Shared Tasks",
month = jul,
year = "2026",
address = "San Diego, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.smm4h-1.35/",
pages = "222--224",
ISBN = "979-8-89176-432-3",
abstract = "This article presents a system description for our work as part of Task 5 of the SMM4H-HeaRD 2026 workshop. We fine-tune pretrained BERT and BiomedBERT models and further enhance them using custom feature augmentation techniques. Incorporating these engineered features results in improved performance, with the best model achieving a validation F1 score of 0.8419 and an evaluation phase F1 score of 0.753."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bansal-etal-2026-halelab">
<titleInfo>
<title>HALELab-NITK at #SMM4H-HeaRD2026: Inclusion of Feature Engineering for Detection of Patient Metadata in SARS-CoV2 Sequencing Articles</title>
</titleInfo>
<name type="personal">
<namePart type="given">Aakarsh</namePart>
<namePart type="family">Bansal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abhishek</namePart>
<namePart type="family">Srinivas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sowmya</namePart>
<namePart type="family">Kamath S.</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 11th Social Media Mining for Health Research and Applications (SMM4H-HeaRD 2026) Workshop and Shared Tasks</title>
</titleInfo>
<name type="personal">
<namePart type="given">Guillermo</namePart>
<namePart type="family">Lopez-Garcia</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">San Diego, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-432-3</identifier>
</relatedItem>
<abstract>This article presents a system description for our work as part of Task 5 of the SMM4H-HeaRD 2026 workshop. We fine-tune pretrained BERT and BiomedBERT models and further enhance them using custom feature augmentation techniques. Incorporating these engineered features results in improved performance, with the best model achieving a validation F1 score of 0.8419 and an evaluation phase F1 score of 0.753.</abstract>
<identifier type="citekey">bansal-etal-2026-halelab</identifier>
<location>
<url>https://aclanthology.org/2026.smm4h-1.35/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>222</start>
<end>224</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T HALELab-NITK at #SMM4H-HeaRD2026: Inclusion of Feature Engineering for Detection of Patient Metadata in SARS-CoV2 Sequencing Articles
%A Bansal, Aakarsh
%A Srinivas, Abhishek
%A Kamath S., Sowmya
%Y Lopez-Garcia, Guillermo
%Y Gonzalez-Hernandez, Graciela
%S Proceedings of the 11th Social Media Mining for Health Research and Applications (SMM4H-HeaRD 2026) Workshop and Shared Tasks
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, United States
%@ 979-8-89176-432-3
%F bansal-etal-2026-halelab
%X This article presents a system description for our work as part of Task 5 of the SMM4H-HeaRD 2026 workshop. We fine-tune pretrained BERT and BiomedBERT models and further enhance them using custom feature augmentation techniques. Incorporating these engineered features results in improved performance, with the best model achieving a validation F1 score of 0.8419 and an evaluation phase F1 score of 0.753.
%U https://aclanthology.org/2026.smm4h-1.35/
%P 222-224
Markdown (Informal)
[HALELab-NITK at #SMM4H-HeaRD2026: Inclusion of Feature Engineering for Detection of Patient Metadata in SARS-CoV2 Sequencing Articles](https://aclanthology.org/2026.smm4h-1.35/) (Bansal et al., SMM4H 2026)
ACL