Skip to main content
SpringerLink
Log in

Part-of-speech- and syntactic-aware graph convolutional network for aspect-level sentiment classification

  • Published:
Multimedia Tools and Applications Aims and scope Submit manuscript

Abstract

Aspect-level sentiment classification is a task within the realm of fine-grained sentiment analysis that focuses on identifying the sentiment polarity specific to a particular aspect of review data. However, most existing methods fail to account for the unique expression and language style used in review data, which limits their sentiment classification performance. To address this issue, we propose a novel method called Part-of-Speech- and Syntactic-Aware Graph Convolutional Network (PSA-GCN) that aims to integrate part-of-speech (POS) information and syntactic knowledge into word embeddings. Specifically, we simplify the complex POS tags into six basic categories. At the same time, we only consider the connection relationship between words in the syntax tree that does not involve dependency types, in order to avoid the inaccuracies of overly-subdivided POS tags and the adverse effects caused by syntax dependencies of erroneous types on sentiment analysis. By incorporating these components into our model, the PSA-GCN is able to enhance the representation power of word embeddings and thus improve the performance in aspect-level sentiment classification. PSA-GCN first extracts part-of-speech tags and the syntactic parse tree to model the linguistic information present in the review data. It then considers the sentiment priors of different part-of-speech pairs holistically to construct a part-of-speech dependency graph, and a syntactic dependency graph utilizing the syntactic information from the parse tree. These graphs are initialized with Bert embeddings, and graph reasoning is performed to obtain the final part-of-speech and syntactic-aware language representation. Finally, aspect-level sentiment polarity is obtained through the classification of the final language representations. Our experiments on Restaurant, Laptop, and Twitter datasets reveal that PSA-GCN outperforms baseline models significantly in all three datasets.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2

Similar content being viewed by others

Data availability

The datasets used in our paper, namely the Laptops and Restaurant dataset from SemEval-2014 Task 4 Subtask 2, and the ACL Twitter Social dataset, are both open-source and publicly available. The Laptops and Restaurant dataset can be accessed through the SemEval-2014 Task 4 official page, and the ACL Twitter Social dataset is available from its respective repository. We adhere to all guidelines and terms of use associated with these datasets.

References

  1. Chen ZM, Wei XS, Wang P et al (2019) Multi-label image recognition with graph convolutional networks. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 5177–5186

  2. Devlin J, Chang MW, Lee K et al (2019) BERT: Pre-training of deep bidi-rectional transformers for language understanding. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers). Association for Computational Linguistics, Minneapolis, Minnesota, pp 4171–4186

  3. Dong L, Wei F, Tan C et al (2014a) 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

  4. Dong L, Wei F, Tan C et al (2014b) 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). Association for Computational Linguistics, Baltimore, Maryland, pp 49–54

  5. Hong D, Gao L, Yao J et al (2020) Graph convolutional networks for hyper-spectral image classification. IEEE Trans Geosci Remote Sens 59(7):5966–5978

    Article  ADS  Google Scholar 

  6. Huang B, Guo R, Zhu Y et al (2022) Aspect-level sentiment analysis with aspect-specific context position information. Knowl Based Syst 243:108473

    Article  Google Scholar 

  7. Jeong C, Jang S, Park E et al (2020) A context-aware citation recommendation model with bert and graph convolutional networks. Scientometrics 124(3):1907–1922

    Article  CAS  Google Scholar 

  8. Ke P, Ji H, Liu S et al (2019) Sentilare: Sentiment-aware language representation learning with linguistic knowledge. arXiv preprint arXiv:1911.02493

  9. Kipf TN, Welling M (2016) Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907

  10. Li R, Chen H, Feng F et al (2021) Dual graph convolutional networks for aspect-based sentiment analysis. In: Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pp 6319–6329

  11. Li W, Li Y, Liu W et al (2022) An influence maximization method based on crowd emotion under an emotion-based attribute social network. Inf Process Manage 59(2):102818

  12. Liu B (2012) Sentiment analysis and opinion mining. Synth Lect Hum Lang Technol 5(1):1–167

    ADS  Google Scholar 

  13. Peng H, Xu L, Bing L et al (2020) Knowing what, how and why: A near complete solution for aspect-based sentiment analysis. Proceedings of the AAAI Conference on Artificial Intelligence 34(05):8600–8607

    Article  Google Scholar 

  14. Phan HT, Nguyen NT, Hwang D (2022) Convolutional attention neural network over graph structures for improving the performance of aspect-level sentiment analysis. Inf Sci 589:416–439

    Article  Google Scholar 

  15. Phan MH, Ogunbona PO (2020) Modelling context and syntactical features for aspect-based sentiment analysis. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp 3211–3220

  16. Pontiki M, Galanis D, Pavlopoulos J et al (2014) SemEval-2014 task 4: Aspect based sentiment analysis. In: Proceedings of the 8th International Workshop on Semantic Evaluation (SemEval 2014). Association for Computational Linguistics, Dublin, Ireland, pp 27–35

  17. Qin A, Shang Z, Tian J et al (2018) Spectral-spatial graph convolutional networks for semisupervised hyperspectral image classification. IEEE Geosci Remote Sens Lett 16(2):241–245

    Article  ADS  Google Scholar 

  18. Quan C, Ren F (2014) Target based review classification for fine-grained sentiment analysis. Int J Innov Comput Inf Control 10(1):257–268

    MathSciNet  Google Scholar 

  19. Said B, Lathamaheswari M, Singh PK et al (2022) An intelligent traffic control system using neutrosophic sets, rough sets, graph theory, fuzzy sets and its extended approach: A literature review. Neutrosophic Sets and Systems, vol 50/2022: An International Journal in Information Science and Engineering p 10

  20. Shuang K, Gu M, Li R et al (2021) Interactive pos-aware network for aspect-level sentiment classification. Neurocomputing 420:181–196

    Article  Google Scholar 

  21. Song Y, Wang J, Jiang T et al (2019) Attentional encoder network for targeted sentiment classification. arXiv preprint arXiv:1902.09314

  22. Tian Y, Chen G, Song Y (2021) Enhancing aspect-level sentiment analysis with word dependencies. In: Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pp 3726–3739

  23. Wang K, Shen W, Yang Y et al (2020a) Relational graph attention network for aspect-based sentiment analysis. arXiv preprint arXiv:2004.12362

  24. Wang K, Shen W, Yang Y et al (2020b) Relational graph attention network for aspect-based sentiment analysis. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics, Online, pp 3229–3238

  25. Wang Y, Huang M, Zhu X et al (2016) Attention-based lstm for aspect-level sentiment classification. In: Proceedings of the 2016 conference on empirical methods in natural language processing, pp 606–615

  26. Wu H, Zhang Z, Shi S et al (2022) Phrase dependency relational graph attention network for aspect-based sentiment analysis. Knowl Based Syst 236:107736

  27. Yang H, Zeng B, Yang J et al (2021) A multi-task learning model for chinese-oriented aspect polarity classification and aspect term extraction. Neurocomputing 419:344–356

    Article  Google Scholar 

  28. Zeng B, Yang H, Xu R et al (2019) Lcf: A local context focus mechanism for aspect-based sentiment classification. Appl Sci 9(16):3389

    Article  Google Scholar 

  29. Zeng J, Liu T, Jia W et al (2022) Relation construction for aspect-level sentiment classification. Inf Sci 586:209–223

    Article  Google Scholar 

  30. Zhang C, Li Q, Song D (2019) Aspect-based sentiment classification with aspect-specific graph convolutional networks. arXiv preprint arXiv:1909.03477

  31. Zhao P, Hou L, Wu O (2020) Modeling sentiment dependencies with graph convolutional networks for aspect-level sentiment classification. Knowl Based Syst 193:105443

  32. Zhao Q, Feng X (2022) Utilizing citation network structure to predict paper citation counts: A deep learning approach. J Informetr 16(1):101235

  33. Zhao Q, Niu J, Liu X (2022) Als-mrs: Incorporating aspect-level sentiment for abstractive multi-review summarization. Knowl Based Syst 258:109942

  34. Zhou J, Huang JX, Chen Q et al (2019) Deep learning for aspect-level sentiment classification: survey, vision, and challenges. IEEE Access 7:78454–78483

    Article  Google Scholar 

  35. Zhou J, Chen Q, Huang JX et al (2020) Position-aware hierarchical transfer model for aspect-level sentiment classification. Inf Sci 513:1–16

    Article  Google Scholar 

  36. Zhu L, Xu M, Zhu Z et al (2023) Multiscale feature aggregation network for aspect sentiment triplet extraction. Appl Intell

Download references

Acknowledgements

This work was supported in part by the National Natural Science Foundation of China under Grants 62072354, 61972302, 62276203 and 62072355, in part by the Key Research and Development Program of Shaanxi Province of China under Grants 2022GY-057 and 2021ZDLGY07-04, in part by the Foundation of National Key Laboratory of Human Factors Engineering under Grant 6142222210101, in part by the Fundamental Research Funds for the Central Universities under Grant QTZX23084, QTZX23105, and QTZX23108, and in part by the Science and Technology Program of Guangzhou under Grant SL2022A04J00303.

Author information

Authors and Affiliations

  1. School of Computer Science and Technology, Xidian University, Xi’an, 710071, Shaanxi, China

    Yumin Tian, Ruifeng Yue, Di Wang, Jinhui Liu & Xiao Liang

Authors
  1. Yumin Tian
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Ruifeng Yue
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Di Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Jinhui Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Xiao Liang
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Di Wang.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Tian, Y., Yue, R., Wang, D. et al. Part-of-speech- and syntactic-aware graph convolutional network for aspect-level sentiment classification. Multimed Tools Appl 83, 28793–28806 (2024). https://doi.org/10.1007/s11042-023-16671-5

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11042-023-16671-5

Keywords

Search

Navigation