@inproceedings{ozturk-etal-2026-automated,
title = "Automated Screening of Antibacterial Nanoparticle Literature: Dataset Curation and Model Evaluation",
author = {Ozturk, Alperen and
{\"O}zate{\c{s}}, {\c{S}}aziye Bet{\"u}l and
Root, Sophia Bahar and
Violi, Angela and
Kotov, Nicholas and
VanEpps, J. Scott and
Emre, Emine Sumeyra Turali},
editor = "Demberg, Vera and
Inui, Kentaro and
Marquez, Llu{\'i}s",
booktitle = "Proceedings of the 19th Conference of the {E}uropean Chapter of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
month = mar,
year = "2026",
address = "Rabat, Morocco",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.eacl-long.20/",
pages = "454--465",
ISBN = "979-8-89176-380-7",
abstract = "Antimicrobial resistance is a growing global health threat, driving interest in nanoparticle-based alternatives to conventional antibiotics. Inorganic nanoparticles (NPs) with intrinsic antibacterial properties show significant promise; however, efficiently identifying relevant studies from the rapidly expanding literature remains a major challenge. This step is crucial for enabling computational approaches that aim to model and predict NP efficacy based on physicochemical and structural features. In this study, we explore the effectiveness of traditional machine learning and deep learning methods in classifying scientific abstracts in the domain of NP-based antimicrobial research. We introduce the ``Antibacterial Inorganic NAnoparticles Dataset'' AINA of 7,910 articles, curated to distinguish intrinsic antibacterial NPs from studies focusing on drug carriers or surface-bound applications. Our comparative evaluation shows that a fine-tuned BioBERT classifier achieved the highest macro F1 (0.82), while a lightweight SVM model with TF-IDF features remained competitive (0.78), highlighting their utility in low-resource settings. AINA enables reproducible, large-scale identification of intrinsically bactericidal inorganic NPs. By reducing noise from non-intrinsic contexts, this work provides a foundation for mechanism-aware screening, database construction, and predictive modeling in antimicrobial NP research."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ozturk-etal-2026-automated">
<titleInfo>
<title>Automated Screening of Antibacterial Nanoparticle Literature: Dataset Curation and Model Evaluation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alperen</namePart>
<namePart type="family">Ozturk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Şaziye</namePart>
<namePart type="given">Betül</namePart>
<namePart type="family">Özateş</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sophia</namePart>
<namePart type="given">Bahar</namePart>
<namePart type="family">Root</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Angela</namePart>
<namePart type="family">Violi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nicholas</namePart>
<namePart type="family">Kotov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">J</namePart>
<namePart type="given">Scott</namePart>
<namePart type="family">VanEpps</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Emine</namePart>
<namePart type="given">Sumeyra</namePart>
<namePart type="given">Turali</namePart>
<namePart type="family">Emre</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Vera</namePart>
<namePart type="family">Demberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kentaro</namePart>
<namePart type="family">Inui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lluís</namePart>
<namePart type="family">Marquez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Rabat, Morocco</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-380-7</identifier>
</relatedItem>
<abstract>Antimicrobial resistance is a growing global health threat, driving interest in nanoparticle-based alternatives to conventional antibiotics. Inorganic nanoparticles (NPs) with intrinsic antibacterial properties show significant promise; however, efficiently identifying relevant studies from the rapidly expanding literature remains a major challenge. This step is crucial for enabling computational approaches that aim to model and predict NP efficacy based on physicochemical and structural features. In this study, we explore the effectiveness of traditional machine learning and deep learning methods in classifying scientific abstracts in the domain of NP-based antimicrobial research. We introduce the “Antibacterial Inorganic NAnoparticles Dataset” AINA of 7,910 articles, curated to distinguish intrinsic antibacterial NPs from studies focusing on drug carriers or surface-bound applications. Our comparative evaluation shows that a fine-tuned BioBERT classifier achieved the highest macro F1 (0.82), while a lightweight SVM model with TF-IDF features remained competitive (0.78), highlighting their utility in low-resource settings. AINA enables reproducible, large-scale identification of intrinsically bactericidal inorganic NPs. By reducing noise from non-intrinsic contexts, this work provides a foundation for mechanism-aware screening, database construction, and predictive modeling in antimicrobial NP research.</abstract>
<identifier type="citekey">ozturk-etal-2026-automated</identifier>
<location>
<url>https://aclanthology.org/2026.eacl-long.20/</url>
</location>
<part>
<date>2026-03</date>
<extent unit="page">
<start>454</start>
<end>465</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Automated Screening of Antibacterial Nanoparticle Literature: Dataset Curation and Model Evaluation
%A Ozturk, Alperen
%A Özateş, Şaziye Betül
%A Root, Sophia Bahar
%A Violi, Angela
%A Kotov, Nicholas
%A VanEpps, J. Scott
%A Emre, Emine Sumeyra Turali
%Y Demberg, Vera
%Y Inui, Kentaro
%Y Marquez, Lluís
%S Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2026
%8 March
%I Association for Computational Linguistics
%C Rabat, Morocco
%@ 979-8-89176-380-7
%F ozturk-etal-2026-automated
%X Antimicrobial resistance is a growing global health threat, driving interest in nanoparticle-based alternatives to conventional antibiotics. Inorganic nanoparticles (NPs) with intrinsic antibacterial properties show significant promise; however, efficiently identifying relevant studies from the rapidly expanding literature remains a major challenge. This step is crucial for enabling computational approaches that aim to model and predict NP efficacy based on physicochemical and structural features. In this study, we explore the effectiveness of traditional machine learning and deep learning methods in classifying scientific abstracts in the domain of NP-based antimicrobial research. We introduce the “Antibacterial Inorganic NAnoparticles Dataset” AINA of 7,910 articles, curated to distinguish intrinsic antibacterial NPs from studies focusing on drug carriers or surface-bound applications. Our comparative evaluation shows that a fine-tuned BioBERT classifier achieved the highest macro F1 (0.82), while a lightweight SVM model with TF-IDF features remained competitive (0.78), highlighting their utility in low-resource settings. AINA enables reproducible, large-scale identification of intrinsically bactericidal inorganic NPs. By reducing noise from non-intrinsic contexts, this work provides a foundation for mechanism-aware screening, database construction, and predictive modeling in antimicrobial NP research.
%U https://aclanthology.org/2026.eacl-long.20/
%P 454-465
Markdown (Informal)
[Automated Screening of Antibacterial Nanoparticle Literature: Dataset Curation and Model Evaluation](https://aclanthology.org/2026.eacl-long.20/) (Ozturk et al., EACL 2026)
ACL