Skip to main content
SpringerLink
Log in

Generic framework for multilingual short text categorization using convolutional neural network

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

Abstract

Online social media is a powerful source of information that can influence users’ decisions. Due to the huge volume of data generated by such media, many researches have been done to automate text categorization. However, finding useful information to satisfy user’s needs is not an easy task. There are many challenges to overcome especially in short text categorization that in addition to being a time-consuming and costly process, short messages have misspellings, typos, irony words and lack of context. To solve these challenges, this article proposes GM-ShorT, a Generic framework for Multilingual Short Text Categorization based on Convolutional Neural Network (CNN). For this, GM-ShorT collects online social media data. Such data were used as input to CNN that is combined with a word embedding mechanism to categorize short text messages. We explored several architectures for CNN and show that GM-ShorT can be used in multilingual Short text categorization with an accuracy of 13.58% higher when compared to other classical approaches.

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

Notes

  1. https://www.smrfoundation.org/nodexl

  2. https://keras.io/

  3. https://scikit-learn.org

  4. https://pypi.org/project/gensim/

  5. Available https://github.com/enmili/multilingualDataset

References

  1. Bengio Y, Ducharme R, Vincent P, Jauvin C (2003) A neural probabilistic language model. J Mach Learn Res 3:1137

    MATH  Google Scholar 

  2. Caragea C, Silvescu A, Tapia AH (2016) Identifying informative messages in disaster events using convolutional neural networks. In: International conference on information systems for crisis response and management, pp 137–147

  3. Georgakopoulos SV, Tasoulis SK, Vrahatis AG, Plagianakos VP (2018) Convolutional neural networks for toxic comment classification. In: Proceedings of the 10th hellenic conference on artificial intelligence, pp 1–6

  4. Geraldo Filho P, Villas L A, Gonçalves V P, Pessin G, Loureiro A A, Ueyama J (2019) Energy-efficient smart home systems: infrastructure and decision-making process. Internet Things 5:153

    Article  Google Scholar 

  5. Hartmann N, Fonseca E, Shulby C, Treviso M, Rodrigues J, Aluisio S (2017) Portuguese word embeddings: evaluating on word analogies and natural language tasks. arXiv:1708.06025

  6. Johnson R, Zhang T (2014) Effective use of word order for text categorization with convolutional neural networks. arXiv:1412.1058

  7. Kim Y (2014) Convolutional neural networks for sentence classification. arXiv:1408.5882

  8. Lai S, Xu L, Liu K, Zhao J (2015) Recurrent convolutional neural networks for text classification. In: Twenty-ninth AAAI conference on artificial intelligence

  9. Lu Y, Sakamoto K, Shibuki H, Mori T (2017) Construction of a multilingual annotated corpus for deeper sentiment understanding in social media. Inf Media Technol 12:111

    Google Scholar 

  10. Lu Y, Sakamoto K, Shibuki H, Mori T (2017) Are deep learning methods better for twitter sentiment analysis. In: Proceedings of the 23rd annual meeting of natural language processing (Japan), pp 787–790

  11. Mandelbaum A, Shalev A (2016) Word embeddings and their use in sentence classification tasks. arXiv:1610.08229

  12. Merchant R M, Elmer S, Lurie N (2011) Integrating social media into emergency-preparedness efforts. New Engl J Med 365(4):289

    Article  Google Scholar 

  13. Mikolov T, Sutskever I, Chen K, Corrado GS, Dean J (2013) Distributed representations of words and phrases and their compositionality. In: Advances in neural information processing systems, pp 3111–3119

  14. Neto J, Filho G, Mano L, Ueyama J (2018) Verbo: voice emotion recognition database in Portuguese language. J Comput Sci 14(11):1420

    Article  Google Scholar 

  15. Nguyen D T, Joty S, Imran M, Sajjad H, Mitra P (2016) Applications of online deep learning for crisis response using social media information. arXiv:1610.01030

  16. Oliveira D F, Chan K S (2019) The effects of trust and influence on the spreading of low and high quality information. Phys A: Stat Mech Appl 525:657

    Article  Google Scholar 

  17. Rocha Filho G P, Meneguette R I, Maia G, Pessin G, Gonçalves V P, Weigang L, Ueyama J, Villas L A (2020) A fog-enabled smart home solution for decision-making using smart objects. Future Gener Comput Syst 103:18

    Article  Google Scholar 

  18. Sakaki T, Okazaki M, Matsuo Y (2010) Earthquake shakes Twitter users: real-time event detection by social sensors. ACM, pp 851–860, DOI Proceedings of the 19th international conference on World wide web, (to appear in print)

  19. Sebastiani F (2002) Machine learning in automated text categorization. ACM Comput Surv (CSUR) 34(1):1

    Article  Google Scholar 

  20. Simon T, Goldberg A, Adini B (2015) Socializing in emergencies—a review of the use of social media in emergency situations. Int J Inf Manag 35(5):609

    Article  Google Scholar 

  21. Sosa P M, Sadigh S (2016) Twitter sentiment analysis with neural networks. Academia. edu

  22. Steiner-Correa F, Viedma-del Jesus M I, Lopez-Herrera A (2018) A survey of multilingual human-tagged short message datasets for sentiment analysis tasks. Soft Comput 22(24):8227

    Article  Google Scholar 

  23. Sun F, Belatreche A, Coleman S, McGinnity TM, Li Y (2014) Pre-processing online financial text for sentiment classification: a natural language processing approach. In: 2014 IEEE conference on computational intelligence for financial engineering & economics (CIFEr). IEEE, pp 122–129

  24. Vilas A F, Redondo R P D, Crockett K, Owda M, Evans L (2019) Twitter permeability to financial events: an experiment towards a model for sensing irregularities. Multimed Tools Appl 78(7):9217

    Article  Google Scholar 

  25. Wang J, Wang Z, Zhang D, Yan J (2017) Combining knowledge with deep convolutional neural networks for short text classification. In: IJCAI, pp 2915–2921

  26. Yang Y, Zheng L, Zhang J, Cui Q, Li Z, Yu PS (2018) TI-CNN: convolutional neural networks for fake news detection. arXiv:1806.00749

  27. Zhang X, LeCun Y (2017) Which encoding is the best for text classification in Chinese, English, Japanese and Korean? arXiv:1708.02657

  28. Zhang Y, Wallace B (2015) A sensitivity analysis of (and practitioners’ guide to) convolutional neural networks for sentence classification. arXiv:1510.03820

  29. Zhang X, Zhao J, LeCun Y (2015) Character-level convolutional networks for text classification. In: Advances in neural information processing systems, pp 649–657

Download references

Author information

Authors and Affiliations

  1. Department of Computer Science, University of Brasília, Brasília, DF, Brazil

    Liriam Enamoto, Li Weigang & Geraldo P. Rocha Filho

Authors
  1. Liriam Enamoto
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Li Weigang
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Geraldo P. Rocha Filho
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Liriam Enamoto.

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

Enamoto, L., Weigang, L. & Filho, G.P.R. Generic framework for multilingual short text categorization using convolutional neural network. Multimed Tools Appl 80, 13475–13490 (2021). https://doi.org/10.1007/s11042-020-10314-9

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11042-020-10314-9

Keywords

Search

Navigation