TY - JOUR

T1 - GL-GCN

T2 - Global and Local Dependency Guided Graph Convolutional Networks for aspect-based sentiment classification

AU - Zhu, Xiaofei

AU - Zhu, Ling

AU - Guo, Jiafeng

AU - Liang, Shangsong

AU - Dietze, Stefan

N1 - Funding Information: This work was supported by the National Natural Science Foundation of China [grant number 61722211 ]; the Federal Ministry of Education and Research, Germany [grant number 01LE1806A ]; the Beijing Academy of Artificial Intelligence, China [grant number BAAI2019ZD0306 ]; and the Technology Innovation and Application Development of Chongqing, China [grant number cstc2020jscx-dxwtBX0014 ].

PY - 2021/12/30

Y1 - 2021/12/30

N2 - Aspect-based sentiment classification, which aims at identifying the sentiment polarity of a sentence towards the specified aspect, has become a crucial task for sentiment analysis. Existing methods have proposed effective models and achieved satisfactory results, but they mainly focus on exploiting local structure information of a given sentence, such as locality, sequentiality or syntactical dependency constraints within the sentence. Recently, some research works, which utilizes global dependency information, has attracted increasing interest and significantly boosts the performance of text classification. In this paper, we simultaneously introduce both global structure information and local structure information into the task of aspect-based sentiment classification, and propose a novel aspect-based sentiment classification approach, i.e., Global and Local Dependency Guided Graph Convolutional Networks (GL-GCN). In particular, we exploit the syntactic dependency structure as well as sentence sequential information (e.g., the output of BiLSTM) to mine the local structure information of a sentence. On the other hand, we construct a word-document graph using the entire corpus to reveal the global dependency information between words. In addition, an attention mechanism is leveraged to effectively fuse both global and local dependency structure signals. Extensive experiments are conducted on five benchmark datasets in terms of both Accuracy and F1-Score, and the results illustrate that our proposed framework outperforms state-of-the-art methods for aspect-based sentiment classification. The model is implemented using PyTorch and is trained on GPU GeForce GTX 2080 Ti.

AB - Aspect-based sentiment classification, which aims at identifying the sentiment polarity of a sentence towards the specified aspect, has become a crucial task for sentiment analysis. Existing methods have proposed effective models and achieved satisfactory results, but they mainly focus on exploiting local structure information of a given sentence, such as locality, sequentiality or syntactical dependency constraints within the sentence. Recently, some research works, which utilizes global dependency information, has attracted increasing interest and significantly boosts the performance of text classification. In this paper, we simultaneously introduce both global structure information and local structure information into the task of aspect-based sentiment classification, and propose a novel aspect-based sentiment classification approach, i.e., Global and Local Dependency Guided Graph Convolutional Networks (GL-GCN). In particular, we exploit the syntactic dependency structure as well as sentence sequential information (e.g., the output of BiLSTM) to mine the local structure information of a sentence. On the other hand, we construct a word-document graph using the entire corpus to reveal the global dependency information between words. In addition, an attention mechanism is leveraged to effectively fuse both global and local dependency structure signals. Extensive experiments are conducted on five benchmark datasets in terms of both Accuracy and F1-Score, and the results illustrate that our proposed framework outperforms state-of-the-art methods for aspect-based sentiment classification. The model is implemented using PyTorch and is trained on GPU GeForce GTX 2080 Ti.

KW - Aspect-based sentiment classification

KW - Attention mechanism

KW - Graph convolutional networks

KW - Sentiment analysis

UR - http://www.scopus.com/inward/record.url?scp=85112487831&partnerID=8YFLogxK

U2 - 10.1016/j.eswa.2021.115712

DO - 10.1016/j.eswa.2021.115712

M3 - Article

AN - SCOPUS:85112487831

VL - 186

JO - Expert systems with applications

JF - Expert systems with applications

SN - 0957-4174

M1 - 115712

ER -