Skip to main content
main-content
Top

Hint

Swipe to navigate through the articles of this issue

Published in: International Journal of Data Science and Analytics 1/2022

07-03-2022 | Regular Paper

Learning from word semantics to sentence syntax by graph convolutional networks for aspect-based sentiment analysis

Authors: Anan Dai, Xiaohui Hu, Jianyun Nie, Jinpeng Chen

Published in: International Journal of Data Science and Analytics | Issue 1/2022

Login to get access
share
SHARE

Abstract

Fine-grained sentiment analysis is currently a main focus in the field of natural language processing. In line with the significance of the semantics and the syntax, both semantic- and syntactic-based approaches are dedicatedly devised and developed. However, the highly integrating of the semantic and syntactic information is still challenging, which leads to the misinterpretation of the sentence. In this work, we propose a human cognition-based method for aspect-based sentiment analysis (ABSA), which establishes the learning from word semantics to sentence syntax. A dual-channel semantic learning graph convolutional networks (GCNs) is devised to capture both the general semantics and the structural semantics of words. Subsequently, a syntactic GCN for sentence syntactic structure learning is carried out. As such, the understanding of the given sentence is performed in line with the human processing practice. Our model is evaluated on five public datasets on the tasks of ABSA. Experimental results reveal that the proposed model is a competitive alternative comparing to the state-of-the-arts methods.
Footnotes
1
The source code is accessible below: https://​github.​com/​snowblue2/​DSS-GCN.
 
Literature
1.
go back to reference Li, H., Xue, Y., Zhao, H., Hu, X., Peng, S.: Co-attention Networks for Aspect-level Sentiment Analysis, pp. 200–209. Springer, Berlin (2019) Li, H., Xue, Y., Zhao, H., Hu, X., Peng, S.: Co-attention Networks for Aspect-level Sentiment Analysis, pp. 200–209. Springer, Berlin (2019)
2.
go back to reference Kim, S.-M. & Hovy, E. Determining the sentiment of opinions. In: COLING 2004: Proceedings of the 20th International Conference on Computational Linguistics, pp. 1367–1373 (2004) Kim, S.-M. & Hovy, E. Determining the sentiment of opinions. In: COLING 2004: Proceedings of the 20th International Conference on Computational Linguistics, pp. 1367–1373 (2004)
3.
go back to reference Wang, Y., Huang, M., Zhu, X., Zhao, L.: Attention-based LSTM for aspect-level sentiment classification. In: Proceedings of the 2016 conference on empirical methods in natural language processing, pp. 606–615 (2016) Wang, Y., Huang, M., Zhu, X., Zhao, L.: Attention-based LSTM for aspect-level sentiment classification. In: Proceedings of the 2016 conference on empirical methods in natural language processing, pp. 606–615 (2016)
4.
go back to reference Tay, Y., Tuan, L. A., Hui, S. C.: Learning to attend via word-aspect associative fusion for aspect-based sentiment analysis. In: Thirty-Second AAAI Conference on Artificial Intelligence (2018) Tay, Y., Tuan, L. A., Hui, S. C.: Learning to attend via word-aspect associative fusion for aspect-based sentiment analysis. In: Thirty-Second AAAI Conference on Artificial Intelligence (2018)
5.
go back to reference Sun, K., Zhang, R., Mensah, S., Mao, Y., Liu, X.: Aspect-level sentiment analysis via convolution over dependency tree. In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP–IJCNLP), pp. 5679–5688 (2019) Sun, K., Zhang, R., Mensah, S., Mao, Y., Liu, X.: Aspect-level sentiment analysis via convolution over dependency tree. In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP–IJCNLP), pp. 5679–5688 (2019)
6.
go back to reference Zhang, C., Li, Q., Song, D.: Aspect-based sentiment classification with aspect-specific graph convolutional networks. In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP–IJCNLP), pp. 4560–4570 (2019) Zhang, C., Li, Q., Song, D.: Aspect-based sentiment classification with aspect-specific graph convolutional networks. In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP–IJCNLP), pp. 4560–4570 (2019)
7.
go back to reference Saffran, J.R.: Statistical language learning: mechanisms and constraints. Current Dir. Psychol. Sci. 12(4), 110–114 (2003) CrossRef Saffran, J.R.: Statistical language learning: mechanisms and constraints. Current Dir. Psychol. Sci. 12(4), 110–114 (2003) CrossRef
8.
go back to reference Levin, B.: English Verb. Classes and Alternations: A Preliminary Investigation. University of Chicago press, Chicago (1993) Levin, B.: English Verb. Classes and Alternations: A Preliminary Investigation. University of Chicago press, Chicago (1993)
9.
go back to reference Brooke, J.: A semantic approach to automated text sentiment analysis. Ph.D. thesis, Department of Linguistics-Simon Fraser University (2009) Brooke, J.: A semantic approach to automated text sentiment analysis. Ph.D. thesis, Department of Linguistics-Simon Fraser University (2009)
10.
go back to reference Nelson, K.: Concept, word, and sentence: interrelations in acquisition and development. Psychol. Rev. 81(4), 267 (1974) CrossRef Nelson, K.: Concept, word, and sentence: interrelations in acquisition and development. Psychol. Rev. 81(4), 267 (1974) CrossRef
11.
12.
go back to reference Chen, Z., Ren, J.: Short text embedding for clustering based on word and topic semantic information, 61–70 (IEEE, 2019) Chen, Z., Ren, J.: Short text embedding for clustering based on word and topic semantic information, 61–70 (IEEE, 2019)
13.
go back to reference Van Valin, R.D., van Valin Jr, R.D., van Valin Jr, R.D., LaPolla, R.J., LaPolla, R.J.: Syntax: Structure, Meaning, and Function. Cambridge University Press, Cambridge (1997) CrossRef Van Valin, R.D., van Valin Jr, R.D., van Valin Jr, R.D., LaPolla, R.J., LaPolla, R.J.: Syntax: Structure, Meaning, and Function. Cambridge University Press, Cambridge (1997) CrossRef
14.
go back to reference Chen, P., Sun, Z., Bing, L., Yang, W.: Recurrent attention network on memory for aspect sentiment analysis. In: Proceedings of the 2017 conference on empirical methods in natural language processing, pp. 452–461 (2017) Chen, P., Sun, Z., Bing, L., Yang, W.: Recurrent attention network on memory for aspect sentiment analysis. In: Proceedings of the 2017 conference on empirical methods in natural language processing, pp. 452–461 (2017)
15.
go back to reference Dong, L., Wei, F., Tan, C., Tang, D., Zhou, M., Xu, K.: Adaptive recursive neural network for target-dependent twitter sentiment classification. In: Proceedings of the 52nd annual meeting of the association for computational linguistics (volume 2: Short papers), pp. 49–54 (2014) Dong, L., Wei, F., Tan, C., Tang, D., Zhou, M., Xu, K.: Adaptive recursive neural network for target-dependent twitter sentiment classification. In: Proceedings of the 52nd annual meeting of the association for computational linguistics (volume 2: Short papers), pp. 49–54 (2014)
16.
go back to reference He, R., Lee, W. S., Ng, H. T., Dahlmeier, D.: Effective attention modeling for aspect-level sentiment classification, 1121–1131 (2018) He, R., Lee, W. S., Ng, H. T., Dahlmeier, D.: Effective attention modeling for aspect-level sentiment classification, 1121–1131 (2018)
17.
go back to reference Kipf, T. N., Welling, M.: Semi-supervised classification with graph convolutional networks. ICLR 2017 (2017) Kipf, T. N., Welling, M.: Semi-supervised classification with graph convolutional networks. ICLR 2017 (2017)
18.
go back to reference Zhang, Y.-D., Satapathy, S.C., Guttery, D.S., Górriz, J.M., Wang, S.-H.: Improved breast cancer classification through combining graph convolutional network and convolutional neural network. Inf. Process. Manag. 58(2), 102439 (2021) CrossRef Zhang, Y.-D., Satapathy, S.C., Guttery, D.S., Górriz, J.M., Wang, S.-H.: Improved breast cancer classification through combining graph convolutional network and convolutional neural network. Inf. Process. Manag. 58(2), 102439 (2021) CrossRef
19.
go back to reference Wang, S.-H., Govindaraj, V., Gorriz, J. M., Zhang, X., Zhang, Y.-D.: Explainable diagnosis of secondary pulmonary tuberculosis by graph rank-based average pooling neural network. J. Ambient Intell. Humanized Comput. 1–14 (2021) Wang, S.-H., Govindaraj, V., Gorriz, J. M., Zhang, X., Zhang, Y.-D.: Explainable diagnosis of secondary pulmonary tuberculosis by graph rank-based average pooling neural network. J. Ambient Intell. Humanized Comput. 1–14 (2021)
20.
go back to reference Marcheggiani, D., Titov, I.: Encoding sentences with graph convolutional networks for semantic role labeling, 1506–1515 (2017) Marcheggiani, D., Titov, I.: Encoding sentences with graph convolutional networks for semantic role labeling, 1506–1515 (2017)
21.
go back to reference Bastings, J., Titov, I., Aziz, W., Marcheggiani, D., Sima’an, K.: Graph convolutional encoders for syntax-aware neural machine translation, 1957–1967 (2017) Bastings, J., Titov, I., Aziz, W., Marcheggiani, D., Sima’an, K.: Graph convolutional encoders for syntax-aware neural machine translation, 1957–1967 (2017)
22.
go back to reference Yao, L., Mao, C., Luo, Y.: Graph convolutional networks for text classification 33, 7370–7377 (2019) Yao, L., Mao, C., Luo, Y.: Graph convolutional networks for text classification 33, 7370–7377 (2019)
23.
go back to reference Liang, B., Yin, R., Gui, L., Du, J. & Xu, R. Jointly learning aspect-focused and inter-aspect relations with graph convolutional networks for aspect sentiment analysis, 150–161 (2020) Liang, B., Yin, R., Gui, L., Du, J. & Xu, R. Jointly learning aspect-focused and inter-aspect relations with graph convolutional networks for aspect sentiment analysis, 150–161 (2020)
24.
go back to reference Zhang, M., Qian, T.: Convolution over hierarchical syntactic and lexical graphs for aspect level sentiment analysis, 3540–3549 (2020) Zhang, M., Qian, T.: Convolution over hierarchical syntactic and lexical graphs for aspect level sentiment analysis, 3540–3549 (2020)
25.
go back to reference Wang, K., Shen, W., Yang, Y., Quan, X., Wang, R.: Relational graph attention network for aspect-based sentiment analysis, 3229–3238 (2020) Wang, K., Shen, W., Yang, Y., Quan, X., Wang, R.: Relational graph attention network for aspect-based sentiment analysis, 3229–3238 (2020)
26.
go back to reference Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, Ł., Polosukhin, I.: Attention is all you need. In: Advances in neural information processing systems, pp. 5998–6008 (2017) Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, Ł., Polosukhin, I.: Attention is all you need. In: Advances in neural information processing systems, pp. 5998–6008 (2017)
27.
go back to reference Tang, H., Ji, D., Li, C., Zhou, Q.: Dependency graph enhanced dual-transformer structure for aspect-based sentiment classification, 6578–6588 (2020) Tang, H., Ji, D., Li, C., Zhou, Q.: Dependency graph enhanced dual-transformer structure for aspect-based sentiment classification, 6578–6588 (2020)
28.
go back to reference Lang, E., Maienborn, C.: Two-level semantics: Semantic form and conceptual structure. Edited by Claudia Maienborn Klaus von Heusinger 114 (2011) Lang, E., Maienborn, C.: Two-level semantics: Semantic form and conceptual structure. Edited by Claudia Maienborn Klaus von Heusinger 114 (2011)
29.
go back to reference Pennington, J., Socher, R., Manning, C. D.: Glove: Global vectors for word representation, 1532–1543 (2014) Pennington, J., Socher, R., Manning, C. D.: Glove: Global vectors for word representation, 1532–1543 (2014)
30.
go back to reference Maas, A. et al. Learning word vectors for sentiment analysis, 142–150 (2011) Maas, A. et al. Learning word vectors for sentiment analysis, 142–150 (2011)
31.
go back to reference Mikolov, T., Chen, K., Corrado, G., Dean, J.: Efficient estimation of word representations in vector space. arXiv preprint arXiv:​1301.​3781 (2013) Mikolov, T., Chen, K., Corrado, G., Dean, J.: Efficient estimation of word representations in vector space. arXiv preprint arXiv:​1301.​3781 (2013)
32.
go back to reference Wang, R., Fu, B., Fu, G., Wang, M.: In: Deep and cross network for ad click predictions, 1–7 (2017) Wang, R., Fu, B., Fu, G., Wang, M.: In: Deep and cross network for ad click predictions, 1–7 (2017)
34.
go back to reference Pontiki, M., Galanis, D., Papageorgiou, H., Manandhar, S. & Androutsopoulos, I. Semeval-2015 task 12: Aspect based sentiment analysis, 486–495 (2015) Pontiki, M., Galanis, D., Papageorgiou, H., Manandhar, S. & Androutsopoulos, I. Semeval-2015 task 12: Aspect based sentiment analysis, 486–495 (2015)
35.
go back to reference Pontiki, M. et al. Semeval-2016 task 5: Aspect based sentiment analysis, 19–30 (2016) Pontiki, M. et al. Semeval-2016 task 5: Aspect based sentiment analysis, 19–30 (2016)
36.
go back to reference Zheng, Y., Zhang, R., Mensah, S., Mao, Y.: Replicate, walk, and stop on syntax. Effective Neural Netw. Model Aspect-level Sentiment Classif 34, 9685–9692 (2020) Zheng, Y., Zhang, R., Mensah, S., Mao, Y.: Replicate, walk, and stop on syntax. Effective Neural Netw. Model Aspect-level Sentiment Classif 34, 9685–9692 (2020)
Metadata
Title
Learning from word semantics to sentence syntax by graph convolutional networks for aspect-based sentiment analysis
Authors
Anan Dai
Xiaohui Hu
Jianyun Nie
Jinpeng Chen
Publication date
07-03-2022
Publisher
Springer International Publishing
Published in
International Journal of Data Science and Analytics / Issue 1/2022
Print ISSN: 2364-415X
Electronic ISSN: 2364-4168
DOI
https://doi.org/10.1007/s41060-022-00315-2

Other articles of this Issue 1/2022

International Journal of Data Science and Analytics 1/2022 Go to the issue

Premium Partner