SentiFuse: Hierarchical Sentiment-Aware Pre-Training with Aspect-Level Contrastive Learning for Multi-Domain Sentiment Analysis
Journal of Computer Science Innovations and Research · 05.06.2026 · 1 (1) · 15-24
DOI: 10.69055/jcsir.v1i1.3 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Computer Science Innovations and Research, online erschienen am 05.06.2026. Verfasst von Esraa Shihab. Die Arbeit nennt 32 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Sentiment analysis is a core task in natural language processing with wide-ranging applications in opinion mining, market intelligence, and social media analytics. Despite impressive progress on single-domain benchmarks, state-of-the-art transformer models still exhibit substantial performance degradation when applied across domains with divergent linguistic styles and aspect vocabularies a phenomenon we term cross-domain sentiment brittleness. In this paper, we propose SentiFuse, a hierarchical sentiment-aware pre-training framework that incorporates aspect-level contrastive learning to build representations that generalize robustly across domains. SentiFuse introduces three components: (i) a Sentiment-Masked Language Model (SMLM) pre-training objective that selectively masks sentiment-bearing tokens to encourage the model to learn polarity-grounded contextual representations; (ii) an Aspect-Level Contrastive (ALC) loss that pulls together representations of the same aspect expressed with different sentiment carriers, while pushing apart conflicting sentiments on the same aspect; and (iii) a Hierarchical Sentiment Aggregation (HSA) decoder that integrates token-, phrase-, and sentence-level sentiment signals during fine-tuning. We evaluate SentiFuse on four widely-used real-world benchmark datasets: SST-2 (Stanford Sentiment Treebank), IMDb Large Movie Reviews, SemEval-2014 Task 4 (Laptop and Restaurant), and Amazon Product Reviews (Electronics). SentiFuse achieves accuracy of 97.3% on SST-2, 97.8% on IMDb, macro-F1 of 88.6% on SemEval-2014 Laptop, and 91.2% on SemEval-2014 Restaurant, surpassing DeBERTa-large by margins of 0.8%, 0.4%, 3.1%, and 2.4% respectively. Ablation studies confirm that all three components contribute meaningfully, with the ALC loss yielding the largest gain (+1.9% on SemEval Laptop). Our analysis demonstrates that SentiFuse transfers sentiment knowledge more reliably across product categories and review genres than domain-agnostic pre-training alone.
Zitieren
APA
Shihab, E. (2026). SentiFuse: Hierarchical Sentiment-Aware Pre-Training with Aspect-Level Contrastive Learning for Multi-Domain Sentiment Analysis. Journal of Computer Science Innovations and Research, 1(1), 15-24. https://doi.org/10.69055/jcsir.v1i1.3
Vancouver
Shihab E. SentiFuse: Hierarchical Sentiment-Aware Pre-Training with Aspect-Level Contrastive Learning for Multi-Domain Sentiment Analysis. Journal of Computer Science Innovations and Research. 2026;1(1):15-24. doi:10.69055/jcsir.v1i1.3
BibTeX
@article{Shihab2026,
author = {Shihab, Esraa},
title = {SentiFuse: Hierarchical Sentiment-Aware Pre-Training with Aspect-Level Contrastive Learning for Multi-Domain Sentiment Analysis},
journal = {Journal of Computer Science Innovations and Research},
year = {2026},
volume = {1},
number = {1},
pages = {15--24},
doi = {10.69055/jcsir.v1i1.3}
}
EUVIMED