Skip to main content

Advertisement

Springer Nature Link
Log in

Improving Sentiment Classification Performance through Coaching Architectures

  • Published:
Cognitive Computation Aims and scope Submit manuscript

Abstract

Intelligent systems have been developed for years to solve specific tasks automatically. An important issue emerges when the information used by these systems exhibits a dynamic nature and evolves. This fact adds a level of complexity that makes these systems prone to a noticeable worsening of their performance. Thus, their capabilities have to be upgraded to address these new requirements. Furthermore, this problem is even more challenging when the information comes from human individuals and their interactions through language. This issue happens more easily and forcefully in the specific domain of Sentiment Analysis, where feelings and opinions of humans are in constant evolution. In this context, systems are trained with an enormous corpus of textual content, or they include an extensive set of words and their related sentiment values. These solutions are usually static and generic, making their manual upgrading almost unworkable. In this paper, an automatic and interactive coaching architecture is proposed. It includes a ML framework and a dictionary-based system both trained for a specific domain. These systems converse about the outcomes obtained during their respective learning stages by simulating human interactive coaching sessions. This leads to an Active Learning process where the dictionary-based system acquires new information and improves its performance. More than 800, 000 tweets have been gathered and processed for experiments. Outstanding results were obtained when the proposed architecture was used. Also, the lexicon was updated with the prior and new words related to the corpus used which is important to reach a better sentiment analysis classification.

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

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

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

Explore related subjects

Discover the latest articles and news from researchers in related subjects, suggested using machine learning.

Notes

  1. https://microtc.readthedocs.io/en/latest/

  2. https://github.com/INGEOTEC/microtc

References

  1. Schiffer MB. The material life of human beings: artifacts, behavior and communication. Routledge; 2002.

    Book  Google Scholar 

  2. Broadbent DE. Perception and communication. Elsevier; 2013.

    Google Scholar 

  3. Conquergood D. Beyond the text: Toward a performative cultural politics. The future of performance studies: Visions and revisions; 1998. p. 25–36.

    Google Scholar 

  4. Gruzitis N, Barzdins G. Polysemy in controlled natural language texts. In: International Workshop on Controlled Natural Language, Springer. 2009. pp 102–120.

  5. Damasio AR. Emotions and feelings. In: Feelings and emotions: The Amsterdam symposium, Cambridge University Press Cambridge. 2004. pp 49–57.

  6. Liu B, et al. Sentiment analysis and subjectivity. Handbook of Natural Language Processing. 2010;2(2010):627–66.

    Google Scholar 

  7. Yue L, Chen W, Li X, Zuo W, Yin M. A survey of sentiment analysis in social media. Knowl Inf Syst. 2019;60(2):617–63.

    Article  Google Scholar 

  8. Lukes J, Søgaard A. Sentiment analysis under temporal shift. In: Proceedings of the 9th workshop on computational approaches to subjectivity, sentiment and social media analysis. 2018. pp 65–71.

  9. de Diego IM, Fernández-Isabel A, Ortega F, Moguerza JM. A visual framework for dynamic emotional web analysis. Knowl-Based Syst. 2018;145:264–73.

    Article  Google Scholar 

  10. Tellez ES, Moctezuma D, Miranda-Jiménez S, Graff M. An automated text categorization framework based on hyperparameter optimization. Knowl-Based Syst. 2018;149:110–23.

    Article  Google Scholar 

  11. Guimarães N, Torgo L, Figueira Á. Twitter as a source for time-and domain-dependent sentiment lexicons. In: Social Network Based Big Data Analysis and Applications, Springer. 2018. pp 1–19.

  12. Zong S, Baheti A, Xu W, Ritter A. Extracting covid-19 events from twitter. 2020. arXiv preprint arXiv:200602567.

  13. Akerkar R, Sajja P. Knowledge-based systems. Jones & Bartlett Publishers. 2009.

  14. Sajja PS, Akerkar R. Knowledge-based systems for development. Advanced Knowledge Based Systems: Model, Applications & Research. 2010;1:1–11.

    Google Scholar 

  15. Chow PK, Yeung DS. A multidimensional knowledge structure. Expert Systems with Applications. 1995;9(2):177–87.

    Article  Google Scholar 

  16. Liebowitz J. The handbook of applied expert systems. cRc Press. 2019.

  17. Reyes-Garcia E, Bouhaï N. Designing Interactive Hypermedia Systems. Wiley Online Library. 2017.

  18. Khazanchi R, Khazanchi P. Artificial intelligence in education: A closer look into intelligent tutoring systems. In: Handbook of Research on Critical Issues in Special Education for School Rehabilitation Practices, IGI Global. 2021. pp 256–277.

  19. Saridakis KM, Dentsoras AJ. Soft computing in engineering design-a review. Adv Eng Inform. 2008;22(2):202–21.

    Article  Google Scholar 

  20. Narang R. Database management systems. Ltd: PHI Learning Pvt; 2018.

    Google Scholar 

  21. Ravi K, Ravi V. A survey on opinion mining and sentiment analysis: tasks, approaches and applications. Knowl-Based Syst. 2015;89:14–46.

    Article  Google Scholar 

  22. Scherer KR, et al. On the nature and function of emotion: A component process approach. Approaches to emotion. 1984. pp 293–317.

  23. Baccianella S, Esuli A, Sebastiani F. Sentiwordnet 3.0: an enhanced lexical resource for sentiment analysis and opinion mining. Lrec. 2010;10:2200–4.

    Google Scholar 

  24. Cambria E, Li Y, Xing FZ, Poria S, Kwok K. Senticnet 6: Ensemble application of symbolic and subsymbolic ai for sentiment analysis. In: Proceedings of the 29th ACM international conference on information & knowledge management. 2020. pp 105–114.

  25. Ahmad M, Aftab S, Muhammad SS, Ahmad S. Machine learning techniques for sentiment analysis: A review. Int J Multidiscip Sci Eng. 2017;8(3):27.

    Google Scholar 

  26. Prabowo R, Thelwall M. Sentiment analysis: A combined approach. J Inform. 2009;3(2):143–57.

    Article  Google Scholar 

  27. Li W, Zhu L, Cambria E. Taylor’s theorem: A new perspective for neural tensor networks. Knowl-Based Syst. 2021;228: 107258.

  28. Dos Santos C, Gatti M. Deep convolutional neural networks for sentiment analysis of short texts. In: Proceedings of COLING 2014, the 25th International Conference on Computational Linguistics: Technical Papers. 2014. pp 69–78.

  29. Devlin J, Chang MW, Lee K, Toutanova K. Bert: Pre-training of deep bidirectional transformers for language understanding. 1810.04805. 2019.

  30. Usama M, Ahmad B, Song E, Hossain MS, Alrashoud M, Muhammad G. Attention-based sentiment analysis using convolutional and recurrent neural network. Futur Gener Comput Syst. 2020;113:571–8.

    Article  Google Scholar 

  31. Liu N, Shen B, Zhang Z, Zhang Z, Mi K. Attention-based sentiment reasoner for aspect-based sentiment analysis. Human-centric Computing and Information Sciences. 2019;9(1):1–17.

    Article  Google Scholar 

  32. Keyvanpour M, Zandian ZK, Heidarypanah M. OMLML: a helpful opinion mining method based on lexicon and machine learning in social networks. Soc Netw Anal Min. 2020;10(1):1–17.

    Article  Google Scholar 

  33. Lu B, Tsou BK. Combining a large sentiment lexicon and machine learning for subjectivity classification. In: 2010 international conference on machine learning and cybernetics, IEEE. 2010. vol 6, pp 3311–3316.

  34. Cambria E. Affective computing and sentiment analysis. IEEE Intell Syst. 2016;31(2):102–7.

    Article  Google Scholar 

  35. Stappen L, Meßner EM, Cambria E, Zhao G, Schuller BW. Muse 2021 challenge: Multimodal emotion, sentiment, physiological-emotion, and stress detection. In: Proceedings of the 29th ACM International Conference on Multimedia. 2021. pp 5706–5707.

  36. Dragoni M, Donadello I, Cambria E. Ontosenticnet 2: Enhancing reasoning within sentiment analysis. IEEE Intell Syst. 2022;37(1):1–8.

    Google Scholar 

  37. Liang B, Su H, Gui L, Cambria E, Xu R. Aspect-based sentiment analysis via affective knowledge enhanced graph convolutional networks. Knowl-Based Syst. 2022;235: 107643.

  38. Ebrahimi M, Yazdavar AH, Sheth A. Challenges of sentiment analysis for dynamic events. IEEE Intell Syst. 2017;32(5):70–5.

    Article  Google Scholar 

  39. Wang Z, Ho SB, Cambria E. Multi-level fine-scaled sentiment sensing with ambivalence handling. Int J Uncertainty Fuzziness Knowledge Based Syst. 2020;28(04):683–97.

    Article  Google Scholar 

  40. Ma L, Ding B, Das S, Swaminathan A. Active learning for ml enhanced database systems. In: Proceedings of the 2020 ACM SIGMOD International Conference on Management of Data. 2020. pp 175–191.

  41. Melville P, Mooney RJ. Diverse ensembles for active learning. In: Proceedings of the twenty-first international conference on Machine learning. 2004 p 74.

  42. Muslea I, Minton S, Knoblock CA. Active learning with multiple views. J Artif Intell Res. 2006;27:203–33.

    Article  MathSciNet  MATH  Google Scholar 

  43. Wei XY, Yang ZQ. Coaching the exploration and exploitation in active learning for interactive video retrieval. IEEE Trans Image Process. 2012;22(3):955–68.

    Article  MathSciNet  MATH  Google Scholar 

  44. Garvey R, Garvey B, Stokes P, Megginson D. Coaching and mentoring: Theory and practice. Sage. 2017.

  45. Saif H, He Y, Fernandez M, Alani H. Adapting sentiment lexicons using contextual semantics for sentiment analysis of twitter. In: European Semantic Web Conference, Springer; 2014. pp 54–63.

  46. Song Y, Gu K, Li H, Sun G. A lexical updating algorithm for sentiment analysis on chinese movie reviews. In: 2017 Fifth International Conference on Advanced Cloud and Big Data (CBD), IEEE; 2017. pp 188–193.

  47. Keshavarz H, Abadeh MS. Alga: Adaptive lexicon learning using genetic algorithm for sentiment analysis of microblogs. Knowl-Based Syst. 2017;122:1–16.

    Article  Google Scholar 

  48. Park S, Lee W, Moon IC. Efficient extraction of domain specific sentiment lexicon with active learning. Pattern Recogn Lett. 2015;56:38–44.

    Article  Google Scholar 

  49. Asghar MZ, Ahmad S, Qasim M, Zahra SR, Kundi FM. Sentihealth: creating health-related sentiment lexicon using hybrid approach. SpringerPlus. 2016;5(1):1–23.

    Article  Google Scholar 

  50. Elshakankery K, Ahmed MF. Hilatsa: A hybrid incremental learning approach for arabic tweets sentiment analysis. Egyptian Informatics Journal. 2019;20(3):163–71.

    Article  Google Scholar 

  51. Rubtsova Y. Reducing the deterioration of sentiment analysis results due to the time impact. Information. 2018;9(8):184.

    Article  Google Scholar 

  52. Cabezas J, Moctezuma D, Fernández-Isabel A, Martín de Diego I. Detecting emotional evolution on twitter during the covid-19 pandemic using text analysis. Int J Environ Res Public Health. 2021;18(13):6981.

    Article  Google Scholar 

  53. Kumar V, Racharla K, Majumdar D. Transfer learning with augmented vocabulary for tweet classification:(grand challenge). In: 2020 IEEE Sixth International Conference on Multimedia Big Data (BigMM), IEEE; 2020. pp 471–475.

  54. Lamsal R. Coronavirus (covid-19) tweets dataset. 2020. https://dx.doi.org/10.21227/781w-ef42, [Online: accessed 1-Aug-2021].

  55. Lamsal R. Design and analysis of a large-scale covid-19 tweets dataset. Appl Intell. 2021;51(5):2790–804.

    Article  Google Scholar 

  56. Loria S. Textblob documentation Release. 2018;015(2):269.

    MathSciNet  Google Scholar 

Download references

Acknowledgements

Research supported by grants from the Spanish Ministry of Economy and Competitiveness under the Retos-Colaboración program: SABERMED (Ref: RTC-2017-6253-1), Retos-Investigación program: MODAS-IN (Ref: RTI-2018-094269-B-I00); and donation of the Titan V GPU by NVIDIA Corporation.

Author information

Authors and Affiliations

  1. Data Science Laboratory, Rey Juan Carlos University, C/ Tulipán, s/n, 28933, Móstoles, Spain

    Alberto Fernández-Isabel, Javier Cabezas & Isaac Martín de Diego

  2. Centro de Investigación en Ciencias de Información Geoespacial, Circuito Tecnopolo Norte 117, Col. Fraccionamiento Tecnopolo Pocitos, 20313, Aguascalientes, México

    Daniela Moctezuma

Authors
  1. Alberto Fernández-Isabel
    View author publications

    You can also search for this author inPubMed Google Scholar

  2. Javier Cabezas
    View author publications

    You can also search for this author inPubMed Google Scholar

  3. Daniela Moctezuma
    View author publications

    You can also search for this author inPubMed Google Scholar

  4. Isaac Martín de Diego
    View author publications

    You can also search for this author inPubMed Google Scholar

Corresponding author

Correspondence to Daniela Moctezuma.

Ethics declarations

Research Involving Human and Animal Participants

This article does not contain any studies with human participants or animals performed by any of the authors.

Conflict of Interest

All the authors declare not to have any conflicts of interest or ethical issues.

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

Fernández-Isabel, A., Cabezas, J., Moctezuma, D. et al. Improving Sentiment Classification Performance through Coaching Architectures. Cogn Comput 15, 1065–1081 (2023). https://doi.org/10.1007/s12559-022-10018-2

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s12559-022-10018-2

Keywords