Syntactic denoising and multi-strategy auxiliary enhancement for aspect-based sentiment analysis
PLOS One · 12.08.2025 · 20 (8) · e0329018
DOI: 10.1371/journal.pone.0329018 ↗Kurz gefasst
Fachartikel in der Zeitschrift PLOS One, online erschienen am 12.08.2025. Verfasst von Lu Liu und 4 weiteren Autor:innen. Beteiligte Einrichtung: Institute of Automation, Qilu University of Technology (Shandong Academy of Sciences), JiNan, ShanDong, China. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 53 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: The Key R&D Program (Science and Technology Cooperation) of Shandong Province, The Innovation Pilot Project for the Integration of Science, Education, and Industry, The Innovation Capability Enhancement Project for Science and Technology oriented Small and Medium sized Enterprises in Shandong Province.
Abstract (Originalsprache)
Aspect-based sentiment analysis (ABSA) aims to identify the sentiment polarity associated with specific aspect terms within sentences. Existing studies have primarily focused on constructing graphs from dependency trees of sentences to extract syntactic features. However, given that public datasets are often derived from online reviews, the syntactic structures of these sentences frequently exhibit irregularities. As a result, the performance of syntactic-based Graph Convolution Network (GCN) models is adversely impacted by the noise introduced during dependency parsing. Moreover, the interaction between syntactic and semantic information in these approaches is often insufficient, which significantly impairs the model’s ability to accurately detect sentiment.To address these challenges, we propose a novel approach called Syntactic Denoising with Multi-strategy Auxiliary Enhancement (SDMAE) for the ABSA task. Specifically, we prune the original dependency tree by focusing on context words with specific part-of-speech features that are critical for conveying the sentiment of aspect terms, and then construct the graph. We introduce a Multi-channel Adaptive Aggregation Module (MAAM), a feature aggregation system that employs a multi-head attention mechanism to integrate semantic and syntactic GCN output representations. Furthermore, we design a multi-strategy task learning framework that incorporates sentiment lexicons and supervised contrastive learning to enhance the model’s performance in aspect sentiment recognition.Comprehensive experiments conducted on four benchmark datasets demonstrate that our approach achieves significant performance improvements compared to several state-of-the-art methods across all evaluated datasets.
Autor:innen und Institutionen
- Institute of Automation, Qilu University of Technology (Shandong Academy of Sciences), JiNan, ShanDong, China.
- Science and Technology Service Platform, Qilu University of Technology (Shandong Academy of Sciences), JiNan, ShanDong, China.
ORCID-Profile: Lu Liu, Yunhai Zhu
Förderung
- The Key R&D Program (Science and Technology Cooperation) of Shandong Province
- The Innovation Pilot Project for the Integration of Science, Education, and Industry
- The Innovation Capability Enhancement Project for Science and Technology oriented Small and Medium sized Enterprises in Shandong Province
Zitieren
APA
Liu, L., Li, D., Yue, C., Gao, X., & Zhu, Y. (2025). Syntactic denoising and multi-strategy auxiliary enhancement for aspect-based sentiment analysis. PLOS One, 20(8), e0329018. https://doi.org/10.1371/journal.pone.0329018
Vancouver
Liu L, Li D, Yue C, Gao X, Zhu Y. Syntactic denoising and multi-strategy auxiliary enhancement for aspect-based sentiment analysis. PLOS One. 2025;20(8):e0329018. doi:10.1371/journal.pone.0329018
BibTeX
@article{Liu2025,
author = {Liu, Lu and Li, Da and Yue, Chuanxu and Gao, Xiaojin and Zhu, Yunhai},
title = {Syntactic denoising and multi-strategy auxiliary enhancement for aspect-based sentiment analysis},
journal = {PLOS One},
year = {2025},
volume = {20},
number = {8},
pages = {e0329018},
doi = {10.1371/journal.pone.0329018}
}
EUVIMED