Data-efficient classification of road inspection texts with a semantic similarity criterion

Mok, CYF; de Silva, L; Reja, VK; Green, S; Brilakis, I

Data-efficient classification of road inspection texts with a semantic similarity criterion

Mok, CYF de Silva, L Reja, VK Green, S Brilakis, I

Permalink

Publisher:: ELSEVIER SCI LTD
Publication Type:: Journal Article
Citation:: Advanced Engineering Informatics, 2025, 67
Issue Date:: 2025-09-01

Open Access

Copyright Clearance Process

Recently Added
In Progress
Open Access

This item is open access.

Adobe PDF

Download Published versionAdobe PDF (6.19 MB)

View on publisher's site

View statistics

Full metadata record

Field	Value	Language
dc.contributor.author	Mok, CYF
dc.contributor.author	de Silva, L
dc.contributor.author	Reja, VK
dc.contributor.author	Green, S
dc.contributor.author	Brilakis, I
dc.date.accessioned	2026-02-09T03:45:26Z
dc.date.available	2026-02-09T03:45:26Z
dc.date.issued	2025-09-01
dc.identifier.citation	Advanced Engineering Informatics, 2025, 67
dc.identifier.issn	1474-0346
dc.identifier.issn	1873-5320
dc.identifier.uri	http://hdl.handle.net/10453/193068
dc.description.abstract	Road maintenance involves manually classifying a large volume of textual data necessary for downstream applications such as raising a maintenance job order. Automation can not only bring significant time and cost savings, but it can also facilitate digitalization efforts like the Road Digital Twin (DT). However, as is the case with many Architecture, Engineering and Construction (AEC) applications, annotated data availability is low, which demands exploration of specialized techniques for resource-constrained settings that have not been focused on in engineering. This work bridges this gap by proposing a data-efficient similarity-based text classifier that aims at effectively utilizing existing domain knowledge and pre-training knowledge of Large Language Models (LLMs) to enable rapid domain adaptation. It reformulates text classification as a similarity comparison task, using semantics directly as a classification criterion. Through a case study on classifying road inspection comments, the proposed classifier outperformed both traditionally fine-tuned and few-shot learning approaches. It attained an f1 score of 0.46 with just one example per class, equivalent to the value for Sentence Transformer Fine-Tuning (SetFit) with 4 examples and Llama3 with 10. Additionally, it is able to keep up with traditional fine-tuning methods when trained with more than 300,000 total examples, achieving an accuracy of more than 95% and f1 of around 0.9. These results indicate that the proposal is competitive against traditionally fine-tuned and few-shot models across all levels of data availability. This versatility significantly elevates the feasibility of deploying an automated text classification pipeline in a complex engineering field like road maintenance.
dc.language	English
dc.publisher	ELSEVIER SCI LTD
dc.relation.ispartof	Advanced Engineering Informatics
dc.relation.isbasedon	10.1016/j.aei.2025.103509
dc.rights	info:eu-repo/semantics/openAccess
dc.subject	08 Information and Computing Sciences, 09 Engineering
dc.subject.classification	Design Practice & Management
dc.subject.classification	40 Engineering
dc.subject.classification	46 Information and computing sciences
dc.title	Data-efficient classification of road inspection texts with a semantic similarity criterion
dc.type	Journal Article
utslib.citation.volume	67
utslib.for	08 Information and Computing Sciences
utslib.for	09 Engineering
pubs.organisational-group	University of Technology Sydney
pubs.organisational-group	University of Technology Sydney/Faculty of Engineering and Information Technology
utslib.copyright.status	open_access	*
dc.rights.license	This work is licensed under a Creative Commons Attribution 4.0 International License (CC BY 4.0). To view a copy of this license, visit https://creativecommons.org/licenses/by/4.0/
dc.date.updated	2026-02-09T03:45:24Z
pubs.publication-status	Published
pubs.volume	67

Abstract:

Road maintenance involves manually classifying a large volume of textual data necessary for downstream applications such as raising a maintenance job order. Automation can not only bring significant time and cost savings, but it can also facilitate digitalization efforts like the Road Digital Twin (DT). However, as is the case with many Architecture, Engineering and Construction (AEC) applications, annotated data availability is low, which demands exploration of specialized techniques for resource-constrained settings that have not been focused on in engineering. This work bridges this gap by proposing a data-efficient similarity-based text classifier that aims at effectively utilizing existing domain knowledge and pre-training knowledge of Large Language Models (LLMs) to enable rapid domain adaptation. It reformulates text classification as a similarity comparison task, using semantics directly as a classification criterion. Through a case study on classifying road inspection comments, the proposed classifier outperformed both traditionally fine-tuned and few-shot learning approaches. It attained an f1 score of 0.46 with just one example per class, equivalent to the value for Sentence Transformer Fine-Tuning (SetFit) with 4 examples and Llama3 with 10. Additionally, it is able to keep up with traditional fine-tuning methods when trained with more than 300,000 total examples, achieving an accuracy of more than 95% and f1 of around 0.9. These results indicate that the proposal is competitive against traditionally fine-tuned and few-shot models across all levels of data availability. This versatility significantly elevates the feasibility of deploying an automated text classification pipeline in a complex engineering field like road maintenance.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/193068