Transformer and statistical models for LCSH assignment: a comparative study in digital libraries.
Purpose: This study aims to examine the effectiveness of machine learning models and ensemble approaches for automating Library of Congress Subject Headings (LCSH) assignment to graduate theses and dissertations, aiming to enhance the efficiency, scalability and accuracy of library subject indexing...
| Publicado en: | Electronic Library Vol. 43; no. 5; pp. 695 - 715 |
|---|---|
| Autor principal: | |
| Formato: | research tables/charts Journal Article |
| Publicado: |
Emerald Publishing Limited
2025
|
| Acceso en línea: | Ver este registro en EBSCOhost |
| fields | @attributes: recordID: 1 pdfLink: plink: https://search.ebscohost.com/login.aspx?direct=true&db=ccm&AN=189668882&site=ehost-live header: @attributes: shortDbName: ccm uiTerm: 189668882 longDbName: CINAHL Complete uiTag: AN controlInfo: bkinfo: dissinfo: jinfo: jid: 02640473 2OJ jtl: Electronic Library issn: 02640473 maglogo: N pubinfo: dt: 2025 vid: 43 iid: 5 pid: 465 pub: Emerald Publishing Limited artinfo: ui: 189668882 189668882 189668882 10.1108/EL-03-2025-0102 189668882 ppf: 695 ppct: 20 formats: tig: atl: Transformer and statistical models for LCSH assignment: a comparative study in digital libraries. aug: au: Usta, Gökhan affil: Library and Documentation Department, İstanbul Teknik Universitesi – Ayazaga Kampusu, Istanbul, Turkey sug: subj: Cataloging Subject Headings Libraries, Electronic Theses and Dissertations Automation Productivity Machine Learning Evaluation Ensemble Learning Evaluation Models, Statistical Evaluation Human Comparative Studies Quasi-Experimental Studies Conceptual Framework Natural Language Processing Prediction Models Paired T-Tests Sensitivity and Specificity Logistic Regression ab: Purpose: This study aims to examine the effectiveness of machine learning models and ensemble approaches for automating Library of Congress Subject Headings (LCSH) assignment to graduate theses and dissertations, aiming to enhance the efficiency, scalability and accuracy of library subject indexing in the digital age. Design/methodology/approach: A comparative quasi-experimental framework assessed five machine learning models (DeBERTa-v3-base, all-mpnet-base-v2, FastText, Omikuji Bonsai, term frequency-inverse document frequency [TF-IDF]) and two ensemble strategies (hybrid: DeBERTa + MPNet; ensemble: FastText + Omikuji Bonsai + TF-IDF) on a dataset of 1,104,600 thesis and dissertation titles across 1,578 LCSH labels, integrating organic and synthetic data. Synthetic titles were generated using large language models and rigorously validated to mitigate bias and prevent dataset imbalance. The performance was evaluated using F1, recall@5, NDCG@5, MRR and computational efficiency metrics (RAM usage and prediction time). Paired t-tests were conducted to confirm statistical significance of key performance differences. Findings: Transformer-based models (DeBERTa-v3-base: F1 0.7348; all-mpnet-base-v2: F1 0.7277) excelled in accuracy, whereas statistical models (e.g. FastText: 0.36 MiB, 0.0006 s) offered superior efficiency. The hybrid model achieved the highest F1 (0.7413) and NDCG@5 (0.8130) and the ensemble model led in recall@5 (0.8824), demonstrating the value of model integration. Ablation results showed that synthetic data substantially improved classification and ranking performance of models. Synthetic data improved dataset balance, enhancing model generalization. Originality/value: This study provides a novel comparison of transformer-based and statistical machine learning models for LCSH assignment, validated through both ablation and statistical significance testing, pioneering the use of synthetic data and probability-weighted ensembles to improve accuracy and ranking. It offers actionable insights for library automation, bridging gaps in prior research focused on narrower model sets. pubtype: Academic Journal doctype: research tables/charts Journal Article ougenre: Article language: English refInfo: holdings: @attributes: islocal: N |
|---|