Skip to main content
SpringerLink
Log in

Aspect Based Sentiment Analysis Using Long-Short Term Memory and Weighted N-Gram Graph-Cut

  • Published:
Cognitive Computation Aims and scope Submit manuscript

Abstract

In the current domain, aspect-based sentiment analysis is a much-explored area in sentiment classification. In this paper, an optimization method, Graph-Cut, is used first time for aspect-based sentiment analysis. In this research, a new concept of N-gram Graph-Cut is applied on aspect-based sentiment analysis. Also, a hybrid approach on a combination of Graph-Cut and long short-term memory (LSTM) algorithm is proposed. In the hybrid approach, knowledge is transferred from 1-g Graph-Cut to LSTM and is applied on two-way and three-way (positive, negative, and neutral) sentiment classification. The 1-g Graph-Cut, 2-g Graph-Cut, and combined 1-g Graph-Cut and LSTM algorithms are applied on restaurant, laptop, and Mams datasets for two-way and three-way classification. It has been observed that for multiword aspect terms in the laptop dataset, it is enhancing the accuracy in both two-way and three-way sentiment classification. Besides, term-based aspect sentiment classification is giving enhanced results in both the ways. Moreover, the proposed hybrid method 1-g Graph-Cut-LSTM gives better accuracy than a single LSTM or CNN model and increases the accuracy by 9% in three-way classification for laptop dataset. One-gram Graph-Cut and 2-g Graph-Cut methods have an advantage over other deep learning methods because they do not require any training, and it is completely unsupervised. The hybrid model 1-g Graph-Cut-LSTM gives better results than LSTM due to the selection of relevant words from a sentence according to its aspect by Graph-Cut method, which is a novel concept.

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

Data Availability

Data available in a public (Kaggle) repository that does not issue datasets with DOIs (non-mandated deposition). The dataset that supports the findings of the study is available from https://www.kaggle.com/datasets/charitarth/semeval-2014-task-4-aspectbasedsentimentanalysis

References

  1. Akhtar MS, Garg T, Ekbal A. Multi-task learning for aspect term extraction and aspect sentiment classification. Neurocomputing. 2020;398:247–56.

    Article  Google Scholar 

  2. Asghar MZ, Khan A, Zahra SR, Ahmad S, Kundi FM. Aspect-based opinion mining framework using heuristic patterns. Clust Comput. 2019;22(3):7181–99.

    Article  Google Scholar 

  3. Chinsha TC, Joseph S. A syntactic approach for aspect based opinion mining. In Proceedings of the 2015 IEEE 9th International Conference on Semantic Computing (IEEE ICSC 2015). 2015;24–31. IEEE.

  4. Vamshi Krishna B, Pandey AK, Siva Kumar AP. Feature based opinion mining and sentiment analysis using fuzzy logic. In Cognitive science and artificial intelligence 2018;79–89. Springer, Singapore.

  5. Perera IK, Caldera HA. Aspect based opinion mining on restaurant reviews. In 2017 2nd IEEE International Conference on Computational Intelligence and Applications (ICCIA) 2017;542–546. IEEE.

  6. Da’u A, Salim N, Rabiu I, Osman A. Weighted aspect-based opinion mining using deep learning for recommender system. Expert Systems with Applications. 2020;140:112871.

  7. Do HH, Prasad PW, Maag A, Alsadoon A. Deep learning for aspect-based sentiment analysis: a comparative review. Expert Syst Appl. 2019;15(118):272–99.

    Article  Google Scholar 

  8. S Jebbara P Cimiano Aspect-based sentiment analysis using a two-step neural network architecture. In Semantic Web Evaluation Challenge 2016;153–167. Springer, Cham.

  9. Ma Y, Peng H, Khan T, Cambria E, Hussain A. Sentic LSTM: a hybrid network for targeted aspect-based sentiment analysis. Cogn Comput. 2018;10(4):639–50.

    Article  Google Scholar 

  10. Zeng D, Dai Y, Li F, Wang J, Sangaiah AK. Aspect based sentiment analysis by a linguistically regularized CNN with gated mechanism. J Intell Fuzzy Syst. 2019;36(5):3971–80.

    Article  Google Scholar 

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

  12. Veyseh AP, Nour N, Dernoncourt F, Tran QH, Dou D, Nguyen TH. Improving aspect-based sentiment analysis with gated graph convolutional networks and syntax-based regulation. arXiv preprint arXiv:2010.13389. 2020.

  13. Li R, Chen H, Feng F, Ma Z, Wang X, Hovy E. 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) 2021;6319–6329.

  14. Chen Z, Xue Y, Xiao L, Chen J, Zhang H. Aspect-based sentiment analysis using graph convolutional networks and co-attention mechanism. In International Conference on Neural Information Processing 2021;441–448. Springer, Cham.

  15. Yang C, Zhang H, Jiang B, Li K. Aspect-based sentiment analysis with alternating coattention networks. Inf Process Manage. 2019;56(3):463–78.

    Article  Google Scholar 

  16. Zhang B, Li X, Xu X, Leung KC, Chen Z, Ye Y. Knowledge guided capsule attention network for aspect-based sentiment analysis. IEEE/ACM Transactions on Audio, Speech, and Language Processing. 2020;17(28):2538–51.

    Article  Google Scholar 

  17. Xue W, Li T. Aspect based sentiment analysis with gated convolutional networks. arXiv preprint arXiv:1805.07043. 2018.

  18. Ma Y, Peng H, Cambria E. Targeted aspect-based sentiment analysis via embedding commonsense knowledge into an attentive LSTM. In Proceedings of the AAAI conference on artificial intelligence; (Vol. 32, No. 1).

  19. Yang M, Jiang Q, Shen Y, Wu Q, Zhao Z, Zhou W. Hierarchical human-like strategy for aspect-level sentiment classification with sentiment linguistic knowledge and reinforcement learning. Neural Netw. 2019;1(117):240–8.

    Article  Google Scholar 

  20. Sivakumar M, Reddy US. Aspect based sentiment analysis of students opinion using machine learning techniques. In 2017 International Conference on Inventive Computing and Informatics (ICICI) 2017;726–731. IEEE.

  21. Afzaal M, Usman M, Fong AC, Fong S, Zhuang Y. Fuzzy aspect based opinion classification system for mining tourist reviews. Adv Fuzzy Syst. 2016;31:2016.

    Google Scholar 

  22. Maheswari SU, Dhenakaran SS. Aspect based fuzzy logic sentiment analysis on social media big data. In 2020 International Conference on Communication and Signal Processing (ICCSP) 2020;0971–0975. IEEE.

  23. Ikram MT, Afzal MT. Aspect based citation sentiment analysis using linguistic patterns for better comprehension of scientific knowledge. Scientometrics. 2019;119(1):73–95.

    Article  Google Scholar 

  24. Kumar R, Pannu HS, Malhi AK. Aspect-based sentiment analysis using deep networks and stochastic optimization. Neural Comput Appl. 2020;32(8):3221–35.

    Article  Google Scholar 

  25. Kumar Gupta D, Srikanth Reddy K, Ekbal A. Pso-asent: Feature selection using particle swarm optimization for aspect based sentiment analysis. In International conference on applications of natural language to information systems 2015;220–233. Springer, Cham.

  26. Mohan I, Moorthi M. Topic flexible aspect based sentiment analysis using minimum spanning tree with Cuckoo search. J Ambient Intell Humaniz Comput. 2021;12(7):7399–406.

    Article  Google Scholar 

  27. Samha AK, Li Y, Zhang J. Aspect-based opinion extraction from customer reviews. arXiv preprint arXiv:1404.1982. 2014.

  28. Mowlaei ME, Abadeh MS, Keshavarz H. Aspect-based sentiment analysis using adaptive aspect-based lexicons. Expert Syst Appl. 2020;15(148):113234.

    Article  Google Scholar 

  29. Federici M, Dragoni M. Knowledge-based approach for aspect-based opinion mining. In Semantic Web Evaluation Challenge 2016;141–152. Springer, Cham.

  30. Federici M, Dragoni M. Aspect-based opinion mining using knowledge bases. In Semantic Web Evaluation Challenge 2017;133–147. Springer, Cham.

  31. Dragoni M, da Costa PC, Tettamanzi AG, Villata S. Combining argumentation and aspect-based opinion mining: the smack system. AI Commun. 2018;31(1):75–95.

    Article  MathSciNet  Google Scholar 

  32. Kastrati Z, Arifaj B, Lubishtani A, Gashi F, Nishliu E. Aspect-based opinion mining of students’ reviews on online courses. In Proceedings of the 2020 6th International Conference on Computing and Artificial Intelligence 2020;510–514.

  33. Sindhu I, Daudpota SM, Badar K, Bakhtyar M, Baber J, Nurunnabi M. Aspect-based opinion mining on student’s feedback for faculty teaching performance evaluation. IEEE Access. 2019;15(7):108729–41.

    Article  Google Scholar 

  34. Mahfiz SL, Romadhony A. Aspect-based opinion mining on beauty product reviews. In 2020 3rd International Seminar on Research of Information Technology and Intelligent Systems (ISRITI) 2020;488–493. IEEE.

  35. Janjua SH, Siddiqui GF, Sindhu MA, Rashid U. Multi-level aspect based sentiment classification of Twitter data: using hybrid approach in deep learning. PeerJ Computer Science. 2021;13(7):e433.

    Article  Google Scholar 

  36. Sivakumar M, Uyyala SR. Aspect-based sentiment analysis of mobile phone reviews using LSTM and fuzzy logic. Int J Data Sci Anal. 2021;12(4):355–67.

    Article  Google Scholar 

  37. Yang Z, Gao Y, Fu X. A decision-making algorithm combining the aspect-based sentiment analysis and intuitionistic fuzzy-VIKOR for online hotel reservation. Ann Oper Res. 2021;1:1–7.

    Google Scholar 

  38. Mary AJ, Arockiam L. ASFuL: Aspect based sentiment summarization using fuzzy logic. In 2017 International Conference on Algorithms, Methodology, Models and Applications in Emerging Technologies (ICAMMAET) 2017;1–5. IEEE.

  39. Jabreel M, Maaroof N, Valls A, Moreno A. Introducing sentiment analysis of textual reviews in a multi-criteria decision aid system. Appl Sci. 2020;11(1):216.

    Article  Google Scholar 

  40. Wang Y, Song W, Tao W, Liotta A, Yang D, Li X, Gao S, Sun Y, Ge W, Zhang W, Zhang W. A systematic review on affective computing: emotion models, databases, and recent advances. Information Fusion. 2022.

  41. Li W, Shao W, Ji S, Cambria E. BiERU: Bidirectional emotional recurrent unit for conversational sentiment analysis. Neurocomputing. 2022;7(467):73–82.

    Article  Google Scholar 

  42. Cambria E, Liu Q, Decherchi S, Xing F, Kwok K. SenticNet 7: a commonsense-based neurosymbolic AI framework for explainable sentiment analysis. Proceedings of LREC 2022.

  43. He K, Mao R, Gong T, Li C, Cambria E. Meta-based self-training and re-weighting for aspect-based sentiment analysis. IEEE Transactions on Affective Computing 2022.

  44. Balaji VR, Suganthi ST, Rajadevi R, Kumar VK, Balaji BS, Pandiyan S. Skin disease detection and segmentation using dynamic Graph-Cut algorithm and classification through Naive Bayes Classifier. Measurement. 2020;15(163):107922.

    Article  Google Scholar 

  45. Liu Z, Song YQ, Sheng VS, Wang L, Jiang R, Zhang X, Yuan D. Liver CT sequence segmentation based with improved U-Net and Graph-Cut. Expert Syst Appl. 2019;15(126):54–63.

    Article  Google Scholar 

  46. Tse L, Mountney P, Klein P, Severini S. Graph-Cut segmentation methods revisited with a quantum algorithm. arXiv preprint arXiv:1812.03050. 2018.

  47. Bulusu A, Palle A, Austin G, Kainth K, Saraf M, Talukder S. Near future stock market forecasting based on chaos theory, sentiment analysis, and quantum computing.

  48. Tay Y, Tuan LA, Hui SC. Learning to attend via word-aspect associative fusion for aspect-based sentiment analysis. In Proceedings of the AAAI conference on artificial intelligence 2018;(Vol. 32, No. 1).

  49. Zhou J, Huang JX, Chen Q, Hu QV, Wang T, He L. Deep learning for aspect-level sentiment classification: survey, vision, and challenges. IEEE access. 2019;30(7):78454–83.

    Article  Google Scholar 

  50. Meng W, Wei Y, Liu P, Zhu Z, Yin H. Aspect based sentiment analysis with feature enhanced attention CNN-BiLSTM. IEEE Access. 2019;11(7):167240–9.

    Article  Google Scholar 

  51. Chen Z, Qian T. Relation-aware collaborative learning for unified aspect-based sentiment analysis. In Proceedings of the 58th annual meeting of the association for computational linguistics 2020;3685–3694.

  52. 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 2016;606–615.

  53. Fan F, Feng Y, Zhao D. Multi-grained attention network for aspect-level sentiment classification. In Proceedings of the 2018 conference on empirical methods in natural language processing 2018;3433–3442.

  54. Jiang Q, Chen L, Xu R, Ao X, Yang M. A challenge dataset and effective models for aspect-based sentiment analysis. 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) 2019;6280–6285.

  55. Wu Z, Ying C, Dai X, Huang S, Chen J. Transformer-based multi-aspect modeling for multi-aspect multi-sentiment analysis. In CCF International Conference on Natural Language Processing and Chinese Computing 2020;546–557. Springer, Cham.

Download references

Author information

Authors and Affiliations

  1. Guru Tegh Bahadur Institute of Technology, New Delhi, India

    Basanti Pal Nandi

  2. Netaji Subhas University of Technology, New Delhi, India

    Amita Jain

  3. Indira Gandhi Delhi Technical University for Women, Delhi, India

    Devendra Kumar Tayal

Authors
  1. Basanti Pal Nandi
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Amita Jain
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Devendra Kumar Tayal
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Basanti Pal Nandi.

Ethics declarations

Competing Interests

The authors declare no competing interests.

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

Nandi, B.P., Jain, A. & Tayal, D.K. Aspect Based Sentiment Analysis Using Long-Short Term Memory and Weighted N-Gram Graph-Cut. Cogn Comput 15, 822–837 (2023). https://doi.org/10.1007/s12559-022-10104-5

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s12559-022-10104-5

Keywords

Search

Navigation