Label-Aware Hierarchical Ranking Model for Multi-Label Text Classification

Multi-label text classification involves assigning multiple relevant categories to a single text, enabling applications in academic indexing, medical diagnostics, and e-commerce. However, existing models often fail to capture complex text-label relationships and lack robust mechanisms for ranking la...

Full description

Saved in:
Bibliographic Details
Main Authors: Lama Ayash, Abdulmohsen Algarni, Omar Alqahtani
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/11129041/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849223102515380224
author Lama Ayash
Abdulmohsen Algarni
Omar Alqahtani
author_facet Lama Ayash
Abdulmohsen Algarni
Omar Alqahtani
author_sort Lama Ayash
collection DOAJ
description Multi-label text classification involves assigning multiple relevant categories to a single text, enabling applications in academic indexing, medical diagnostics, and e-commerce. However, existing models often fail to capture complex text-label relationships and lack robust mechanisms for ranking label relevance, limiting their effectiveness. This paper proposes the Label-Aware Hierarchical Ranking Model, a novel approach that combines contextual embeddings, custom attention mechanisms, and gradient boosting to enhance label ranking. The proposed model integrates text and label embeddings with a contextual similarity attention module to capture text-label relationships and inter-label dependencies, followed by a hierarchical ranking mechanism for refining label prioritization. Experiments conducted on both the ArXiv Academic Paper dataset and the Reuters-21578 dataset demonstrate that the proposed model surpasses state-of-the-art models, achieving Precision@1 scores of 86.90 % and 94.47 %, respectively. These results advance multi-label text classification methodologies, offering more accurate, context-aware, and practically applicable classifications.
format Article
id doaj-art-a5b2a50f65d240e29a2d69f2a6ab70f6
institution Kabale University
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-a5b2a50f65d240e29a2d69f2a6ab70f62025-08-25T23:12:31ZengIEEEIEEE Access2169-35362025-01-011314592514593710.1109/ACCESS.2025.359994411129041Label-Aware Hierarchical Ranking Model for Multi-Label Text ClassificationLama Ayash0https://orcid.org/0000-0002-6268-9072Abdulmohsen Algarni1https://orcid.org/0000-0002-7556-958XOmar Alqahtani2https://orcid.org/0009-0001-6652-3512Department of Computer Science, King Khalid University, Al Faraa, Abha, Aseer, Saudi ArabiaDepartment of Computer Science, King Khalid University, Al Faraa, Abha, Aseer, Saudi ArabiaDepartment of Computer Science, King Khalid University, Al Faraa, Abha, Aseer, Saudi ArabiaMulti-label text classification involves assigning multiple relevant categories to a single text, enabling applications in academic indexing, medical diagnostics, and e-commerce. However, existing models often fail to capture complex text-label relationships and lack robust mechanisms for ranking label relevance, limiting their effectiveness. This paper proposes the Label-Aware Hierarchical Ranking Model, a novel approach that combines contextual embeddings, custom attention mechanisms, and gradient boosting to enhance label ranking. The proposed model integrates text and label embeddings with a contextual similarity attention module to capture text-label relationships and inter-label dependencies, followed by a hierarchical ranking mechanism for refining label prioritization. Experiments conducted on both the ArXiv Academic Paper dataset and the Reuters-21578 dataset demonstrate that the proposed model surpasses state-of-the-art models, achieving Precision@1 scores of 86.90 % and 94.47 %, respectively. These results advance multi-label text classification methodologies, offering more accurate, context-aware, and practically applicable classifications.https://ieeexplore.ieee.org/document/11129041/Multi-label classificationnatural language processingdeep learningneural networkstext classificationattention mechanisms
spellingShingle Lama Ayash
Abdulmohsen Algarni
Omar Alqahtani
Label-Aware Hierarchical Ranking Model for Multi-Label Text Classification
IEEE Access
Multi-label classification
natural language processing
deep learning
neural networks
text classification
attention mechanisms
title Label-Aware Hierarchical Ranking Model for Multi-Label Text Classification
title_full Label-Aware Hierarchical Ranking Model for Multi-Label Text Classification
title_fullStr Label-Aware Hierarchical Ranking Model for Multi-Label Text Classification
title_full_unstemmed Label-Aware Hierarchical Ranking Model for Multi-Label Text Classification
title_short Label-Aware Hierarchical Ranking Model for Multi-Label Text Classification
title_sort label aware hierarchical ranking model for multi label text classification
topic Multi-label classification
natural language processing
deep learning
neural networks
text classification
attention mechanisms
url https://ieeexplore.ieee.org/document/11129041/
work_keys_str_mv AT lamaayash labelawarehierarchicalrankingmodelformultilabeltextclassification
AT abdulmohsenalgarni labelawarehierarchicalrankingmodelformultilabeltextclassification
AT omaralqahtani labelawarehierarchicalrankingmodelformultilabeltextclassification