skip to main content
research-article

Multi-task Fuzzy Clustering–Based Multi-task TSK Fuzzy System for Text Sentiment Classification

Published:18 November 2021Publication History
Skip Abstract Section

Abstract

Text sentiment classification is an important technology for natural language processing. A fuzzy system is a strong tool for processing imprecise or ambiguous data, and it can be used for text sentiment analysis. This article proposes a new formulation of a multi-task Takagi-Sugeno-Kang fuzzy system (TSK FS) modeling, which can be used for text sentiment image classification. Using a novel multi-task fuzzy c-means clustering algorithm, the common (public) information among all tasks and the individual (private) information for each task are extracted. The information about clustering, for example, cluster centers, can be used to learn the antecedent parameters of multi-task TSK fuzzy systems. With the common and individual antecedent parameters obtained, a corresponding multi-task learning mechanism for learning consequent parameters is devised. Accordingly, a multi-task fuzzy clustering–based multi-task TSK fuzzy system (MTFCM-MT-TSK-FS) is proposed. When the proposed model is built, the information conveyed by the fuzzy rules formed is two-fold, including (1) common fuzzy rules representing the inter-task correlation information and (2) individual fuzzy rules depicting the independent information of each task. The experimental results on several text sentiment datasets demonstrate the validity of the proposed model.

REFERENCES

  1. [1] Li Junjie, Li Haoran, Kang Xiaomian, Yang Haitong, and Zong Chengqing. 2018. Incorporating multi-level user preference into document-level sentiment classification. ACM Transactions on Asian and Low-Resource Language Information Processing 18, 1 (2018), 7, 117. Google ScholarGoogle ScholarDigital LibraryDigital Library
  2. [2] Yang Jun, Yang Runqi, Lu Hengyang, Wang Chongjun, and Xie Junyuan. 2019. Multi-entity aspect-based sentiment analysis with context, entity, aspect memory and dependency information. ACM Transactions on Asian and Low-Resource Language Information Processing 18, 4 (2019), 47, 122. Google ScholarGoogle ScholarDigital LibraryDigital Library
  3. [3] Mauro Dragoni and Petrucci Giulio. 2017. A neural word embeddings approach for multi-domain sentiment analysis. IEEE Transactions on Affective Computing 8, 4 (2017), 457470.Google ScholarGoogle ScholarCross RefCross Ref
  4. [4] Amna Dridi and Reforgiato Recupero Diego. 2019. Leveraging semantics for sentiment polarity detection in social media. International Journal of Machine Learning and Cybernetics 10, 8 (2019), 20452055.Google ScholarGoogle ScholarCross RefCross Ref
  5. [5] Viviane Rhoda Ogutu A., Rimiru Richard, and Otieno Calvins. 2019. Target sentiment analysis model with Naïve Bayes and support vector machine for product review classification. International Journal of Computer Science and Information Security 17, 7 (2019), 117.Google ScholarGoogle Scholar
  6. [6] Azeem Mohammad Fazle, Hanmandlu Madasu, and Ahmad Nesar. 2000. Generalization of adaptive neural-fuzzy inference systems. IEEE Transactions on Neural Networks and Learning Systems 11, 6 (2000), 13321346. Google ScholarGoogle ScholarDigital LibraryDigital Library
  7. [7] Leski Jacek M.. 2015. Fuzzy (c + p)-means clustering and its application to a fuzzy rule-based classifier: Towards good generalization and good interpretability. 2015. IEEE Transactions on Fuzzy Systems 23, 4 (2015), 802812.Google ScholarGoogle ScholarDigital LibraryDigital Library
  8. [8] Haque Md. Ansarul and Rahman Tamjid. Sentiment analysis by using fuzzy logic. 2014. International Journal of Computer Science, Engineering and Information Technology 4, 1 (2014), 3348.Google ScholarGoogle ScholarCross RefCross Ref
  9. [9] Dragoni Mauro, Tettamanzi Andrea G. B., and da Costa Pereira Célia. 2014. A fuzzy system for concept-level sentiment analysis. Communications in Computer & Information Science 475 (2014), 2127.Google ScholarGoogle ScholarCross RefCross Ref
  10. [10] Fu Guohong and Wang Xin. 2010. Chinese sentence-level sentiment classification based on fuzzy sets. In Proceedings of the 23rd International Conference on Computational Linguistics: Posters. Association for Computational Linguistics, Beijing, China, 312319. Google ScholarGoogle ScholarDigital LibraryDigital Library
  11. [11] Balkrishna Sathe Jaydeep and Mali Manisha P.. 2017. A hybrid sentiment classification method using neural network and fuzzy logic. In Proceedings of the 11th International Conference on Intelligent Systems and Control (ISCO’17), IEEE, Coimbatore, India. 9396.Google ScholarGoogle Scholar
  12. [12] Zhou Shusen, Chen Qingcai, and Wang Xiaolong. 2014. Fuzzy deep belief networks for semisupervised sentiment classification. Neurocomputing 131, 5 (2014), 312322. Google ScholarGoogle ScholarDigital LibraryDigital Library
  13. [13] Serrano-Guerrero Jesus, Romero Francisco P., and Olivas Jose A.. 2021. Fuzzy logic applied to opinion mining: A review. Knowledge-Based Systems 222, 6 (2021), 107018.Google ScholarGoogle ScholarCross RefCross Ref
  14. [14] Fatima Es-Sabery, Abdellatif Hair, Junaid Qadir, Beatriz Sainz-De-Abajo, Begona Garcia-Zapirain, Isabel de la Torre-Diez. 2021. Sentence-level classification using parallel fuzzy deep learning classifier. IEEE Access 9 (2021), 1794317985.Google ScholarGoogle ScholarCross RefCross Ref
  15. [15] Youness Madani, Mohammed Erritali, Jamaa Bengourram, Francoise Sailhan. 2020. Social network analysis: Transforming a black and white approach into a grey approach using fuzzy logic system. Journal of Information Technology Research 13, 3 (2020), 142155.Google ScholarGoogle ScholarDigital LibraryDigital Library
  16. [16] Majumder Navonil, Poria Soujanya, Peng Haiyun, Chhaya Niyati, Cambria Erik, and Gelbukh Alexander. 2019. Sentiment and sarcasm classification with multitask learning. IEEE Intelligent Systems 34, 3 (2019), 3843.Google ScholarGoogle ScholarCross RefCross Ref
  17. [17] Kim Hyun, Lee Jong-Hyeok, and Na Seung-Hoon. 2019. Multi-task stack propagation for neural quality estimation. ACM Transactions on Asian and Low-Resource Language Information Processing 18, 4 (2019), 48, 118. Google ScholarGoogle ScholarDigital LibraryDigital Library
  18. [18] Blitzer John, Dredze Mark, and Pereira Fernando. Biographies, Bollywood, boomboxes and blenders: Domain adaptation for sentiment classification. In Proceedings of the 45th Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics, Prague, Czech Republic, 2527.Google ScholarGoogle Scholar
  19. [19] Pan Sinno Jialin, Ni Xiaochuan, Sun Jiantao, Yang Qiang, and Chen Zheng. 2010. Cross-domain sentiment classification via spectral feature alignment. In Proceedings of the 19th International Conference on World Wide Web. Association for Computing Machinery, Raleigh North Carolina USA, 2630. Google ScholarGoogle ScholarDigital LibraryDigital Library
  20. [20] Mishra Abhijit, Kanojia Diptesh, and Bhattacharyya Pushpak. 2016. Predicting readers’ sarcasm understandability by modeling gaze behavior. In Proceedings of the 30th AAAI Conference on Artificial Intelligence. AAAI Press, Phoenix, Arizona, USA, 37473753. Google ScholarGoogle ScholarDigital LibraryDigital Library
  21. [21] Tan Songbo and Zhang Jin. 2008. An empirical study of sentiment analysis for Chinese documents. Expert Systems with Applications 34 (2008), 26222629 Google ScholarGoogle ScholarDigital LibraryDigital Library
  22. [22] Nakov Preslav, and Zesch Torsten. 2016. Computational semantic analysis of language: SemEval-2014 and beyond [J]. Language Resources and Evaluation 50, 1 (2016), 14. Google ScholarGoogle ScholarDigital LibraryDigital Library
  23. [23] Jiang Yizhang, Chung Fu-Lai, Ishibuchi Hisao, Deng Zhaohong, and Wang Shitong. 2014. Multitask TSK fuzzy system modeling by mining intertask common hidden structure. IEEE Transactions on Cybernetics 45, 3 (2014), 534547.Google ScholarGoogle ScholarCross RefCross Ref
  24. [24] Jiang Yizhang, Deng Zhaohong, Chung Fu-Lai, and Wang Shitong. 2015. Multi-task TSK fuzzy system modeling using inter-task correlation information. Information Sciences 298, 3 (2015), 512533. Google ScholarGoogle ScholarDigital LibraryDigital Library
  25. [25] Meisheri Hardik and Khadilkar Harshad. 2018. Learning representations for sentiment classification using multi-task framework. In Proceedings of the 9th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis. Association for Computational Linguistics, Brussels, Belgium, 299308.Google ScholarGoogle ScholarCross RefCross Ref
  26. [26] Akhtar Md Shad, Chauhan Dushyant, Ghosal Deepanway, Poria Soujanya, Ekbal Asif, and Bhattacharyya Pushpak. 2019. Multi-task learning for multi-modal emotion recognition and sentiment analysis. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 370379.Google ScholarGoogle ScholarCross RefCross Ref
  27. [27] Leski Jacek M.. 2004. An -margin nonlinear classifier based on fuzzy if-then rules. IEEE Transactions on Systems, Man, and Cybernetics, Part B 34, 1 (2004), 6876. Google ScholarGoogle ScholarDigital LibraryDigital Library
  28. [28] Juang Chia Feng, Chiu Shih Hsuan, and Jie Shiu Shen. 2007. Fuzzy system learned through fuzzy clustering and support vector machine for human skin color segmentation. IEEE Transactions on Systems, Man, and Cybernetics, Part A 37, 6 (2007), 10771087. Google ScholarGoogle ScholarDigital LibraryDigital Library
  29. [29] Gu Xiaoqing, Chung Fu-Lai, and Wang Shitong. 2017. Bayesian Takagi-Sugeno-Kang fuzzy classifier. IEEE Transactions on Fuzzy Systems 25, 6 (2017), 16551671.Google ScholarGoogle ScholarDigital LibraryDigital Library
  30. [30] Deng Zhaohong, Jiang Yizhang, Choi Kup-Sze, Chung Fu-Lai, and Wang Shitong. 2013. Knowledge-leverage-based TSK fuzzy system modeling. IEEE Transactions on Neural Networks and Learning Systems 24, 8 (2013), 12001212. Google ScholarGoogle ScholarDigital LibraryDigital Library
  31. [31] Leski Jacek M.. 2005. TSK-fuzzy modeling based on ɛ-insensitive learning. IEEE Transactions on Fuzzy Systems 13, 2 (2005), 181193. Google ScholarGoogle ScholarDigital LibraryDigital Library
  32. [32] Tan Songbo and Zhang Jin. 2008. An empirical study of sentiment analysis for Chinese documents. Expert Systems with Applications 34 (2008), 2622—2629. Google ScholarGoogle ScholarDigital LibraryDigital Library
  33. [33] Pontiki M., Galanis D., Pavlopoulos J., Papageorgiou H., Androutsopoulos I., and Manandhar S.. 2014. Semeval-2014 task 4: Aspect based sentiment analysis. In Proceedings of the 8th International Workshop on Semantic Evaluation (SemEval’14), Dublin, Ireland. 2735.Google ScholarGoogle ScholarCross RefCross Ref
  34. [34] Mikolov Tomas, Chen Kai, Corrado Greg, and Dean Jeffrey. 2013. Efficient estimation of word representations in vector space. CoRR abs/1301.3781 (2013). arXiv:1301.3781Google ScholarGoogle Scholar
  35. [35] Zhang Huaping, Liu Qun, Cheng Xueqi, Zhang Hao, and Yu Hongkui. 2003. Chinese lexical analysis using hierarchical hidden Markov model. In Proceedings of the 2nd SIGHAN Workshop on Chinese Language Processing, Sapporo, Japan, July 2003. Association for Computational Linguistics, Sapporo, Japan, 6370. Google ScholarGoogle ScholarDigital LibraryDigital Library
  36. [36] Meng Jiana, Long Yingchun, Yu Yuhai, Zhao Dandan, and Liu Shuang. 2019. Cross-domain text sentiment analysis based on CNN_FT method. Information. 10, 162 (2019), 114.Google ScholarGoogle Scholar
  37. [37] Zhou Ta, Chung Fu-Lai, and Wang Shitong. 2017. Deep TSK fuzzy classifier with stacked generalization and triplely concise interpretability guarantee for large data. IEEE Transactions on Fuzzy Systems 25, 5 (2017), 12071221.Google ScholarGoogle ScholarDigital LibraryDigital Library
  38. [38] Zhang Chen, Li Qiuchi, and Song Dawei. 2019. 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, Hong Kong, China. Association for Computational Linguistics, Hong Kong, China, 45674577.Google ScholarGoogle ScholarCross RefCross Ref
  39. [39] Almiman Ali, Osman Nada, and Torki Marwan. 2020. Deep neural network approach for Arabic community question answering. Alexandria Engineering Journal 59, 6 (2020), 44274434.Google ScholarGoogle ScholarCross RefCross Ref

Index Terms

  1. Multi-task Fuzzy Clustering–Based Multi-task TSK Fuzzy System for Text Sentiment Classification

      Recommendations

      Comments

      Login options

      Check if you have access through your login credentials or your institution to get full access on this article.

      Sign in

      Full Access

      • Published in

        cover image ACM Transactions on Asian and Low-Resource Language Information Processing
        ACM Transactions on Asian and Low-Resource Language Information Processing  Volume 21, Issue 2
        March 2022
        413 pages
        ISSN:2375-4699
        EISSN:2375-4702
        DOI:10.1145/3494070
        Issue’s Table of Contents

        Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].

        Publisher

        Association for Computing Machinery

        New York, NY, United States

        Publication History

        • Published: 18 November 2021
        • Accepted: 1 July 2021
        • Revised: 1 June 2021
        • Received: 1 February 2020
        Published in tallip Volume 21, Issue 2

        Permissions

        Request permissions about this article.

        Request Permissions

        Check for updates

        Qualifiers

        • research-article
        • Refereed

      PDF Format

      View or Download as a PDF file.

      PDF

      eReader

      View online with eReader.

      eReader

      Full Text

      View this article in Full Text.

      View Full Text

      HTML Format

      View this article in HTML Format .

      View HTML Format
      About Cookies On This Site

      We use cookies to ensure that we give you the best experience on our website.

      Learn more

      Got it!