BERT-OntoSent: combining BERT language model with sentiment ontology for enhanced sentiment analysis on social media

Sentiment analysis on social media is vital but challenged by language complexity and context dependency. Existing methods often fall short. This paper presents BERT-OntoSent, a hybrid approach synergizing BERT's contextual power with ontology-based structured knowledge. We provide a detailed m...

Full description

Saved in:
Bibliographic Details
Main Authors: Abdelweheb Gueddes, Mohamed Ali Mahjoub
Format: Article
Language:English
Published: Taylor & Francis Group 2025-07-01
Series:Journal of Information and Telecommunication
Subjects:
Online Access:https://www.tandfonline.com/doi/10.1080/24751839.2025.2528363
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849470204370747392
author Abdelweheb Gueddes
Mohamed Ali Mahjoub
author_facet Abdelweheb Gueddes
Mohamed Ali Mahjoub
author_sort Abdelweheb Gueddes
collection DOAJ
description Sentiment analysis on social media is vital but challenged by language complexity and context dependency. Existing methods often fall short. This paper presents BERT-OntoSent, a hybrid approach synergizing BERT's contextual power with ontology-based structured knowledge. We provide a detailed methodology where the DCWEB-SOBA process transforms text into (aspect, opinion, sentiment) triplets, populating a domain-specific BERT-OntoSent ontology used for fine-tuning BERT. SWRL rules within the ontology then refine BERT's predictions, enhancing robustness, particularly for negation and mixed sentiments, as formalized in our proposed refinement algorithm. We present a comprehensive evaluation demonstrating BERT-OntoSent's effectiveness not only on the SemEval 2016 restaurant benchmark but also across diverse domains, including product reviews (Amazon) and microblogs (Twitter). Our results consistently show significant improvements in accuracy and F1-score compared to BERT-only and ontology-only baselines across these datasets. Furthermore, we report on experimental optimizations for scalability, demonstrating practical performance gains. The findings confirm the robustness and broader applicability of the BERT-OntoSent hybrid approach, establishing the value of LLM-ontology synergy for advanced sentiment analysis.
format Article
id doaj-art-feea0c55d937495cbc4f709a65ce3943
institution Kabale University
issn 2475-1839
2475-1847
language English
publishDate 2025-07-01
publisher Taylor & Francis Group
record_format Article
series Journal of Information and Telecommunication
spelling doaj-art-feea0c55d937495cbc4f709a65ce39432025-08-20T03:25:12ZengTaylor & Francis GroupJournal of Information and Telecommunication2475-18392475-18472025-07-0112310.1080/24751839.2025.2528363BERT-OntoSent: combining BERT language model with sentiment ontology for enhanced sentiment analysis on social mediaAbdelweheb Gueddes0Mohamed Ali Mahjoub1IsitCom, Sousse University, Sousse, TunisiaNational School of Engineers of Sousse, LATIS Laboratory of Advanced Technology and Intelligent Systems, Sousse University, Sousse, TunisiaSentiment analysis on social media is vital but challenged by language complexity and context dependency. Existing methods often fall short. This paper presents BERT-OntoSent, a hybrid approach synergizing BERT's contextual power with ontology-based structured knowledge. We provide a detailed methodology where the DCWEB-SOBA process transforms text into (aspect, opinion, sentiment) triplets, populating a domain-specific BERT-OntoSent ontology used for fine-tuning BERT. SWRL rules within the ontology then refine BERT's predictions, enhancing robustness, particularly for negation and mixed sentiments, as formalized in our proposed refinement algorithm. We present a comprehensive evaluation demonstrating BERT-OntoSent's effectiveness not only on the SemEval 2016 restaurant benchmark but also across diverse domains, including product reviews (Amazon) and microblogs (Twitter). Our results consistently show significant improvements in accuracy and F1-score compared to BERT-only and ontology-only baselines across these datasets. Furthermore, we report on experimental optimizations for scalability, demonstrating practical performance gains. The findings confirm the robustness and broader applicability of the BERT-OntoSent hybrid approach, establishing the value of LLM-ontology synergy for advanced sentiment analysis.https://www.tandfonline.com/doi/10.1080/24751839.2025.2528363Sentiment analysisBERTontologyhybrid approachsocial media
spellingShingle Abdelweheb Gueddes
Mohamed Ali Mahjoub
BERT-OntoSent: combining BERT language model with sentiment ontology for enhanced sentiment analysis on social media
Journal of Information and Telecommunication
Sentiment analysis
BERT
ontology
hybrid approach
social media
title BERT-OntoSent: combining BERT language model with sentiment ontology for enhanced sentiment analysis on social media
title_full BERT-OntoSent: combining BERT language model with sentiment ontology for enhanced sentiment analysis on social media
title_fullStr BERT-OntoSent: combining BERT language model with sentiment ontology for enhanced sentiment analysis on social media
title_full_unstemmed BERT-OntoSent: combining BERT language model with sentiment ontology for enhanced sentiment analysis on social media
title_short BERT-OntoSent: combining BERT language model with sentiment ontology for enhanced sentiment analysis on social media
title_sort bert ontosent combining bert language model with sentiment ontology for enhanced sentiment analysis on social media
topic Sentiment analysis
BERT
ontology
hybrid approach
social media
url https://www.tandfonline.com/doi/10.1080/24751839.2025.2528363
work_keys_str_mv AT abdelwehebgueddes bertontosentcombiningbertlanguagemodelwithsentimentontologyforenhancedsentimentanalysisonsocialmedia
AT mohamedalimahjoub bertontosentcombiningbertlanguagemodelwithsentimentontologyforenhancedsentimentanalysisonsocialmedia