Skip to main content
SpringerLink
Log in

A classified feature representation three-way decision model for sentiment analysis

  • Published:
Applied Intelligence Aims and scope Submit manuscript

Abstract

Binary sentiment analysis uses sentiment dictionaries, TF-IDF, word2vec, and BERT to convert text documents such as product and movie reviews into vectors. Dimensionality reduction by feature selection can effectively reduce the complexity of sentiment analysis. Existing feature selection methods put all samples together and ignore the difference in the feature representation between different categories. For binary sentiment analysis, there are some reviews with uncertain sentiment polarity, three-way decision divides samples into positive (POS) region, negative (NEG) region, and uncertain region (UNC). The model based on the three-way decision is beneficial to process the UNC and improve the effect of binary sentiment analysis. However, how to obtain the optimal feature representation in certain regions respectively to process the uncertain samples is a challenge. In this paper, a classified feature representation three-way decision model is proposed to obtain the optimal feature representation of the positive and negative domains for sentiment analysis. In the positive domain and the negative domain, m- and n-layer feature representations are obtained. The optimal layer with the best performance is selected as the optimal feature representation. The POS region and the NEG region in the testing set are processed by the optimal feature representation, the UNC region is processed by the original feature representation. Experiments on IMDB and Amazon show that the performance of our proposed method in terms of classification accuracy in sentiment analysis is significantly higher than that of the chi-square, principal component analysis, and mutual information methods.

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
Fig. 3
Fig. 4
Fig. 5
Fig. 6

Similar content being viewed by others

References

  1. Ahmad S R, Bakar A A, Yaakub M R (2019) A review of feature selection techniques in sentiment analysis. In: Intelligent data analysis, vol 1, pp 159–189

  2. Mehta P, Chandra S (2019) NICFS: A novel feature selection method applied to lexicon based sentiment analysis. Intell Decis Technol 13(1):41–48

    Article  Google Scholar 

  3. Devlin J, Chang M, Lee K, Toutanova K (2019) BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In: north american chapter of the association for computational linguistics. pp 4171–4186

  4. Tommasel A, Godoy D (2018) A Social-aware online short-text feature selection technique for social media. Information Fusion

  5. Wang Z, Lin Z (2020) Optimal feature selection for Learning-Based algorithms for sentiment classification. Cogn Comput 12(1):238–248

    Article  Google Scholar 

  6. Madasu A, Sivasankar E (2020) Efficient Feature Selection techniques for Sentiment Analysis. Multimed Tools Appl 79(9):6313–6335

    Article  Google Scholar 

  7. Kumar H M K, Harish B S (2019) A new feature selection method for sentiment analysis in short text. J Intell Syst 29(1):1122–1134

    Article  MathSciNet  Google Scholar 

  8. Tripathy A, Agrawal A, Rath S K (2016) Classification of sentiment reviews using n-gram machine learning approach. Expert Syst Appl 57:117–126

    Article  Google Scholar 

  9. Barkha B, Sangeet S (2019) Hybrid attribute based sentiment classification of online reviews for consumer intelligence. Appl Intell 49(1):137–149

    Article  Google Scholar 

  10. Al-Sharuee M T, Liu F, Pratama M (2020) Sentiment analysis: dynamic and temporal clustering of product reviews. Appl Intell:1–20

  11. Huiping C, Lidan W, Shukai D (2016) Sentiment classification model based on word embedding and CNN. Application Research of Computers

  12. Dey R, Hong Y (2018) CompNet: Complementary Segmentation Network for Brain MRI Extraction. In: medical image computing and computer assisted intervention, pp 628– 636

  13. Sabour S, Frosst N, Hinton GE (2017) Dynamic Routing Between Capsules. arXiv Computer Vision and Pattern Recognition

  14. Hochreiter S, Schmidhuber J (1997) Long Short-Term memory. Neural Comput 9(8):1735–1780

    Article  Google Scholar 

  15. Tang D, Qin B, Feng X, Liu T Effective LSTMs for Target-Dependent Sentiment Classification. arXiv Computation and Language

  16. Chen L -C, Lee C -M, Chen M -Y (2020) Exploration of social media for sentiment analysis using deep learning. Soft Comput 24(11):8187–8197. https://doi.org/10.1007/s00500-019-04402-8

    Article  Google Scholar 

  17. Yao Y (2009) Three-Way Decision: An Interpretation of Rules in Rough Set Theory. Rough Sets and Knowledge Technology, 4th International Conference, RSKT 2009, Gold Coast. Proceedings. Springer, Berlin

  18. Fujita H, Gaeta A, Loia V, Orciuoli F (2020) Hypotheses analysis and assessment in counterterrorism activities: a method based on OWA and fuzzy probabilistic rough sets. IEEE Trans Fuzzy Syst 28 (5):831–845. https://doi.org/10.1109/TFUZZ.2019.2955047

    Article  Google Scholar 

  19. Yiyu Y (2018) Three-way decision and granular computing. Int J Approx Reason 103:107–123

    Article  Google Scholar 

  20. Yao Y (2019) Tri-level thinking: models of three-way decision. Int J Mach Learn Cybern 1(5)

  21. Yao Y, Wang S, Deng X (2017) Constructing shadowed sets and three-way approximations of fuzzy sets. Inf Sci:132–153

  22. Zhao X, Miao D, Fujita H (2020) Variable-precision three-way concepts in L-contexts. Int J Approx Reason 130:107– 125

    Article  MathSciNet  Google Scholar 

  23. Yang X, Zhang Y, Fujita H, Liu D, Li T (2020) Local temporal-spatial multi-granularity learning for sequential three-way granular computing. Inf Sci 541:75–97. https://doi.org/10.1016/j.ins.2020.06.020

    Article  MathSciNet  Google Scholar 

  24. Luo J, Fujita H, Yao Y, Qin K (2020) On modeling similarity and three-way decision under incomplete information in rough set theory. Knowl Based Syst 191:105251. https://doi.org/10.1016/j.knosys.2019.105251

    Article  Google Scholar 

  25. Yang D, Deng T, Fujita H (2020) Partial-overall dominance three-way decision models in interval-valued decision systems. Int J Approx Reason 126:308–325. https://doi.org/10.1016/j.ijar.2020.08.014

    Article  MathSciNet  Google Scholar 

  26. Yue X, Chen Y, Miao D, Fujita H (2020) Fuzzy neighborhood covering for three-way classification. Inf Sci 507:795–808. https://doi.org/10.1016/j.ins.2018.07.065

    Article  MathSciNet  Google Scholar 

  27. Li Y, Zhang L, Xu Y, Yao Y, Lau R, Wu Y (2017) Enhancing binary classification by modeling uncertain boundary in Three-Way decisions. IEEE Trans Knowl Data Eng:1–1

  28. Qiao J, Qing Hu B (2018) On transformations from semi-three-way decision spaces to three-way decision spaces based on triangular norms and triangular conorms. Information Ences S0020025517305911

  29. Li H, Zhang L, Zhou X, Huang B (2017) Cost-sensitive sequential three-way decision modeling using a deep neural network. Int J Approx Reason 85:68–78

    Article  MathSciNet  Google Scholar 

  30. Abdel-Basset M, Manogaran G, Mohamed M, Chilamkurti N (2018) Three-way decisions based on neutrosophic sets and AHP-QFD framework for supplier selection problem. Futur Gener Comput Syst 89(DEC.):19–30

    Article  Google Scholar 

  31. Hu F, Wang L, Zhou Y (2018) An oversampling method for imbalance data based on Three-Way decision model. Acta Electron Sin 46(1):135–144

    Google Scholar 

  32. Afridi M K, Azam N, Yao J T, Alanazi E (2018) A three-way clustering approach for handling missing data using GTRS. Int J Approx Reason:11–24

  33. Jiang C, Wu J, Li Z (2018) Adaptive thresholds determination for saving cloud energy using three-way decisions. Cluster Computing

  34. Fujita H, Gaeta A, Loia V, Orciuoli F (2019) Resilience analysis of critical infrastructures: a cognitive approach based on granular computing. IEEE Trans Cybern 49(5):1835–1848. https://doi.org/10.1109/TCYB.2018.2815178

    Article  Google Scholar 

  35. Yao Y (2008) A unified framework of granular computing. Wiley

  36. Yang X, Li T, Fujita H, Liu D, Yao Y (2017) A unified model of sequential three-way decisions and multilevel incremental processing. Knowl-Based Syst 134:172–188

    Article  Google Scholar 

  37. Chen J, Zhang Y P, Zhao S (2016)

  38. Wang T, Li H, Zhang L, Zhou X, Huang B (2020) A three-way decision model based on cumulative prospect theory. Inf Sci 519:74–92. https://doi.org/10.1016/j.ins.2020.01.030

    Article  MathSciNet  Google Scholar 

  39. Li H, Zhang L, Huang B, Zhou X (2019) Cost-Sensitive Dual-Bidirectional Linear discriminant analysis. Inf Sci 510:283–303

    Article  MathSciNet  Google Scholar 

  40. Chung J, Gulcehre C, Cho K, Bengio Y (2014) Empirical evaluation of gated recurrent neural networks on sequence modeling. arXiv Neural and Evolutionary Computing

  41. Harish B S, Revanasiddappa M B (2017) A Comprehensive Survey on various Feature Selection Methods to Categorize Text Documents. Int J Comput Appl 164(8):1–7

    Google Scholar 

  42. Yang Y (1997) A Comparative Study on Feature Selection in Text Categorization. In: Proceedings of Int Conference on Machine Learning

  43. Abbasi A, Chen H, Salem A (2008) Sentiment analysis in multiple languages: Feature selection for opinion classification in Web forums. ACM Trans Inf Syst 26(3):12

    Article  Google Scholar 

  44. Rasool A, Tao R, Kamyab A (2020) GAWA–A feature selection method for hybrid sentiment classification. IEEE Access:8

  45. Madasu A, Elango S (2020) Efficient feature selection techniques for sentiment analysis. Multimed Tools Appl 79(9-10):6313–6335

    Article  Google Scholar 

  46. Wang Z, Lin Z (2020) Optimal feature selection for Learning-Based algorithms for sentiment classification. Cogn Comput 12(1):238–248

    Article  Google Scholar 

  47. Gokalp O, Tasci E, Ugur A (2020) A novel wrapper feature selection algorithm based on iterated greedy metaheuristic for sentiment classification. Expert Syst Appl 146:113176-

  48. Yao Y, Zhang X (2017) Class-specific attribute reducts in rough set theory. Inf Sci:601–618

  49. Zhang L, Zhang B (2014) Quotient Space Based Problem Solving.

  50. Ling Z, Bo Z (2003) Theory of Fuzzy Quotient Space (Methods of Fuzzy Granular Computing). Journal of Software

  51. Chen J, Xu Y (2020) AH3: An Adaptive Hierarchical Feature Representation Model for Three-Way Decision Boundary Processing[J]. International Journal of Advanced Research

Download references

Acknowledgements

This work was supported by the Major Program of the National Social Science Foundation of China (Grant No. 18ZDA032), the National Natural Science Foundation of China (Grant No. 61876001), and the China Scholarship Council.

Author information

Authors and Affiliations

  1. Key Laboratory of Intelligent Computing and Signal Processing, Ministry of Education, Hefei, 230601, China

    Jie Chen, Yue Chen, Yang Xu, Shu Zhao & Yanping Zhang

  2. School of Computer Science and Technology, Anhui University, Hefei, 230601, China

    Jie Chen, Yue Chen, Yang Xu, Shu Zhao & Yanping Zhang

  3. Beijing University of Posts and Telecommunications, Beijing, 10045, China

    Yechen He

Authors
  1. Jie Chen
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Yue Chen
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Yechen He
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Yang Xu
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Shu Zhao
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Yanping Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Shu Zhao.

Ethics declarations

Conflict of interest

The authors declare that they have no conflict of interest.

Additional information

Publisher’s note

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

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Chen, J., Chen, Y., He, Y. et al. A classified feature representation three-way decision model for sentiment analysis. Appl Intell 52, 7995–8007 (2022). https://doi.org/10.1007/s10489-021-02809-1

Download citation

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10489-021-02809-1

Keywords

Search

Navigation