Aspect Sentiment Triplet Extraction with Syntax-Semantics Graph Convolutional Network

Abstract In the traditional task of aspect sentiment triplet extraction, existing approaches typically focus on either syntactic or semantic features independently, failing to leverage the complementary integration of these two types of information. Although graph convolutional network-based approac...

Full description

Saved in:
Bibliographic Details
Main Authors: Jingyun Zhang, Shuwei Xu, Xin Gao, Zhiwei Tang
Format: Article
Language:English
Published: Springer 2025-07-01
Series:International Journal of Computational Intelligence Systems
Subjects:
Online Access:https://doi.org/10.1007/s44196-025-00900-w
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849334237292920832
author Jingyun Zhang
Shuwei Xu
Xin Gao
Zhiwei Tang
author_facet Jingyun Zhang
Shuwei Xu
Xin Gao
Zhiwei Tang
author_sort Jingyun Zhang
collection DOAJ
description Abstract In the traditional task of aspect sentiment triplet extraction, existing approaches typically focus on either syntactic or semantic features independently, failing to leverage the complementary integration of these two types of information. Although graph convolutional network-based approaches have demonstrated impressive performance in triplet extraction tasks, they often ignore distance features and semantic information when capturing sentence information. As a result, the integration of syntactic and semantic information remains suboptimal, negatively impacting sentiment analysis performance. To address this limitation, we propose a novel Syntax-Semantics Graph Convolutional Network for aspect sentiment triplet extraction. Our method first extracts syntactic structural information using the probability matrix of dependency trees, from which a mask matrix is constructed based on the varying distances between words. Next, semantic information is captured via a self-attention mechanism and an aspect-attention mechanism, utilizing an attention score matrix. Finally, an interaction module is introduced to effectively integrate syntactic and semantic features. Extensive experiments on several benchmark datasets demonstrate that our approach significantly outperforms existing baselines, achieving an average F1-score improvement of at least 1.083%.
format Article
id doaj-art-31a67b846ffe4981a9bdf3cd704e8c3e
institution Kabale University
issn 1875-6883
language English
publishDate 2025-07-01
publisher Springer
record_format Article
series International Journal of Computational Intelligence Systems
spelling doaj-art-31a67b846ffe4981a9bdf3cd704e8c3e2025-08-20T03:45:36ZengSpringerInternational Journal of Computational Intelligence Systems1875-68832025-07-0118111710.1007/s44196-025-00900-wAspect Sentiment Triplet Extraction with Syntax-Semantics Graph Convolutional NetworkJingyun Zhang0Shuwei Xu1Xin Gao2Zhiwei Tang3School of Software, Henan UniversitySchool of Software, Henan UniversitySchool of Software, Henan UniversitySchool of Software, Henan UniversityAbstract In the traditional task of aspect sentiment triplet extraction, existing approaches typically focus on either syntactic or semantic features independently, failing to leverage the complementary integration of these two types of information. Although graph convolutional network-based approaches have demonstrated impressive performance in triplet extraction tasks, they often ignore distance features and semantic information when capturing sentence information. As a result, the integration of syntactic and semantic information remains suboptimal, negatively impacting sentiment analysis performance. To address this limitation, we propose a novel Syntax-Semantics Graph Convolutional Network for aspect sentiment triplet extraction. Our method first extracts syntactic structural information using the probability matrix of dependency trees, from which a mask matrix is constructed based on the varying distances between words. Next, semantic information is captured via a self-attention mechanism and an aspect-attention mechanism, utilizing an attention score matrix. Finally, an interaction module is introduced to effectively integrate syntactic and semantic features. Extensive experiments on several benchmark datasets demonstrate that our approach significantly outperforms existing baselines, achieving an average F1-score improvement of at least 1.083%.https://doi.org/10.1007/s44196-025-00900-wAspect-based sentiment analysisAspect sentiment triplet extractionGraph convolutional networkSyntactic information and semantic information
spellingShingle Jingyun Zhang
Shuwei Xu
Xin Gao
Zhiwei Tang
Aspect Sentiment Triplet Extraction with Syntax-Semantics Graph Convolutional Network
International Journal of Computational Intelligence Systems
Aspect-based sentiment analysis
Aspect sentiment triplet extraction
Graph convolutional network
Syntactic information and semantic information
title Aspect Sentiment Triplet Extraction with Syntax-Semantics Graph Convolutional Network
title_full Aspect Sentiment Triplet Extraction with Syntax-Semantics Graph Convolutional Network
title_fullStr Aspect Sentiment Triplet Extraction with Syntax-Semantics Graph Convolutional Network
title_full_unstemmed Aspect Sentiment Triplet Extraction with Syntax-Semantics Graph Convolutional Network
title_short Aspect Sentiment Triplet Extraction with Syntax-Semantics Graph Convolutional Network
title_sort aspect sentiment triplet extraction with syntax semantics graph convolutional network
topic Aspect-based sentiment analysis
Aspect sentiment triplet extraction
Graph convolutional network
Syntactic information and semantic information
url https://doi.org/10.1007/s44196-025-00900-w
work_keys_str_mv AT jingyunzhang aspectsentimenttripletextractionwithsyntaxsemanticsgraphconvolutionalnetwork
AT shuweixu aspectsentimenttripletextractionwithsyntaxsemanticsgraphconvolutionalnetwork
AT xingao aspectsentimenttripletextractionwithsyntaxsemanticsgraphconvolutionalnetwork
AT zhiweitang aspectsentimenttripletextractionwithsyntaxsemanticsgraphconvolutionalnetwork