Skip to main content
SpringerLink
Log in

A Novel Hybrid Model Based on CNN and Bi-LSTM for Arabic Multi-domain Sentiment Analysis

  • Conference paper
  • First Online:
Complex, Intelligent and Software Intensive Systems (CISIS 2023)

Part of the book series: Lecture Notes on Data Engineering and Communications Technologies ((LNDECT,volume 176))

Included in the following conference series:

Abstract

Since Web 2.0 and the freedom to share information, perspectives, and opinions on global events, services, goods, etc., most of the content on social media platforms comes from users. Social media data includes user sentiment-related subjects. Due to its complexity, ambiguity, dialects, shortage of resources, and morphological diversity, little work has been done on Arabic sentiment analysis. This study introduces a novel word embedding model, AraWord2Vec, based on Wor2Vec trained on Wikipedia and the Sentiment Benchmark dataset. We also examined how Wor2Vec embedding models improved classification tasks. Second, a novel CM_BiLSTM deep learning model called Convolutional Max Pooling and Bidirectional LSTM is presented to enhance Arabic sentiment analysis. Our experimental findings revealed the performance of all models on diverse datasets with an accuracy of 98.47% in binary classification; in multi-classes classification, we obtained a high performance of 98.92%.

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

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 229.00
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 299.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

References

  1. Dashtipour, K., et al.: Multilingual sentiment analysis: state of the art and independent comparison of techniques. Cogn. Comput. 8(4), 757–771 (2016)

    Article  Google Scholar 

  2. Kechaou, Z., Ben Ammar, M., Alimi, A.M.: Improving e-learning with sentiment analysis of users' opinions. In: 2011 IEEE Global Engineering Education Conference (EDUCON), pp. 1032–1038 (2011)

    Google Scholar 

  3. Kechaou, Z., Ben Ammar, M., Alimi, A.M.: A new linguistic approach to sentiment automatic processing. In: IEEE ICCI, pp 265–272 (2010)

    Google Scholar 

  4. Kechaou, Z., Wali, A., Ben Ammar, M., Alimi, A.M.: Novel hybrid method for sentiment classification of movie reviews. In: DMIN, pp 415–421 (2010)

    Google Scholar 

  5. Kechaou, Z., Kanoun, S.: A new-arabic-text classification system using a Hidden Markov Model. KES J. 18(4), 201–210 (2014)

    Article  Google Scholar 

  6. Kechaou, Z., Wali, A., Ben Ammar, M., Karray, H., Alimi, A.M.: A novel system for video news’ sentiment analysis. J. Syst. Inform. Technol. 15(1), 24–44 (2013)

    Google Scholar 

  7. Kechaou, Z., Ben Ammar, M., Alimi, A.M.: A multi-agent based system for sentiment analysis of user-generated content. Int. J. Artif. Intell. Tools 22(02), 1350004 (2013)

    Article  Google Scholar 

  8. Al-Moslmi, T., Albared, M., Al-Shabi, A., Omar, N., Abdullah, S.: Arabic senti-lexicon: constructing publicly available language resources for arabic sentiment analysis. J. Inform. Sci. 44(3), 345–362 (2018)

    Article  Google Scholar 

  9. Zaghouan, W.: Critical survey of the freely available Arabic corpora. Comput. Sci. arXiv:1702.07835 (2017)

  10. Aly, M., Atiya, A.: LABR: large-scale arabic book reviews dataset. In: Association of Computational Linguistics (2013)

    Google Scholar 

  11. Abbes, M., Kechaou, Z., Alimi, A.M.: Enhanced deep learning models for sentiment analysis in Arab social media. In: Liu, D., Xie, S., Li, Y., Zhao, D., El-Alfy, E.-S.M. (eds.) ICONIP 2017. LNCS, vol. 10638, pp. 667–676. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-70139-4_68

    Chapter  Google Scholar 

  12. Al Sallab, A., Hajj, H., Badaro, G., Baly, R., El Hajj, W., Shaban, K.B.: Deep learning models for sentiment analysis in Arabic. In: Proceedings of the second workshop on Arabic natural language processing, pp. 9–17 (2015)

    Google Scholar 

  13. Al Sallab, A., Baly, R., Hajj, H., Shaban, K.B., El-Hajj, W., Badaro, G.: AROMA: a recursive deep learning model for opinion mining in Arabic as a low resource language. ACM Trans. Asian Low-Resour. Lang. Inf. Process. 16(4), 25 (2017)

    Article  Google Scholar 

  14. Alayba, A.M., Palade, V., England, M., Iqbal, R.: Arabic language sentiment analysis on health services. In: 1st international workshop on Arabic script analysis and recognition (Asar), pp. 114–118 (2017)

    Google Scholar 

  15. Alayba, A.M., Palade, V., England, M., Iqbal, R.: A combined cnn and lstm model for arabic sentiment analysis. In: Holzinger, A., Kieseberg, P., Tjoa, A.M., Weippl, E. (eds.) Machine Learning and Knowledge Extraction, pp. 179–191 (2018)

    Google Scholar 

  16. Al Azani, S., El-Alfy, E.S.: Emojis-based sentiment classification of Arabic microblogs using deep recurrent neural networks. In: International Conference on computing sciences and engineering, ICCSE, pp. 1–6 (2018)

    Google Scholar 

  17. Chawla, N.V., Bowyer, K.W., Hall, L.O., Kegelmeyer, W.P.: Smote: synthetic minority over-sampling technique. J. Artif. Intell. Res. 321–357 (2015)

    Google Scholar 

  18. Omara, E., Mosa, M., Ismail, N.: Deep convolutional network for Arabic sentiment analysis. In: International Japan–Africa Conference on Electronics, Communications and Computations, JAC-ECC, pp. 155–159 (2018)

    Google Scholar 

  19. Heikal, M., Torki, M., El-Makky, N.: Sentiment analysis of Arabic tweets using deep learning. Procedia Comput. Sci. 142, 114–122 (2018)

    Article  Google Scholar 

  20. Dahou, A., Abd Elaziz, M., Zhou, J., Xiong, S.: Arabic sentiment classification using convolutional neural network and differential evolution algorithm. Comput. Intell. Neurosci. 2019, 2537689 (2019)

    Article  Google Scholar 

  21. Al Smadi, M., Talafha, B., Al Ayyoub, M., Jararweh, Y.: Using long short-term memory deep neural networks for aspect-based sentiment analysis of Arabic reviews. Int. J. Mach. Learn. Cybern. 10(8), 2163–2175 (2019)

    Article  Google Scholar 

  22. Elnagar, A., Al Debsi, R., Einea, O.: Arabic text classification using deep learning models. Inform. Process. Manage. 57(1), 102121 (2020)

    Article  Google Scholar 

  23. Alwehaibi, A., Roy, K.: Comparison of pre-trained word vectors for Arabic text classification using deep learning approach. In: IEEE International Conference on Machine Learning and Applications, ICMLA (2019)

    Google Scholar 

  24. Fawzy, M., Fakhr, M.W., Rizka, M.A.: Sentiment Analysis for Arabic Low Resource Data Using BERT-CNN. In: International Conference on Language Engineering, pp. 24–26 (2022)

    Google Scholar 

  25. Al-Hagree, S., Al-Gaphari, G.: Arabic sentiment analysis on mobile applications using Levenshtein distance algorithm and naive Bayes. In: 2nd International Conference on Emerging Smart Technologies and Applications, pp. 1–6 (2022)

    Google Scholar 

  26. Mikolov, T., Chen, K., Corrado, G., Dean, J.: Efficient estimation of word representations in vector space. In: 1st International Conference on Learning Representations, pp. 1–12 (2013)

    Google Scholar 

  27. Soliman, A.B., Eisa, K., El-Beltagy, S.R.: AraVec: a set of arabic word embedding models for use in Arabic NLP. In: International Conference on Arabic Computational Linguistics (2017)

    Google Scholar 

  28. https://dumps.wikimedia.org/

  29. Elnagar, A., Khalifa, Y.S., Einea, A.: Hotel arabic-reviews dataset construction for sentiment analysis applications. In: Shaalan, K., Hassanien, A.E., Tolba, F. (eds.) Intelligent Natural Language Processing: Trends and Applications. SCI, vol. 740, pp. 35–52. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-67056-0_3

    Chapter  Google Scholar 

  30. Elnagar, A., Einea, O.: BRAD 1.0: Book reviews in Arabic dataset. In: IEEE/ACS International Conference of Computer Systems and Applications, pp. 1–8 (2016)

    Google Scholar 

  31. Attardi, G.: WikiExtractor. GitHub repository. https://github.com/attardi/wikiextractor (2015)

  32. Nabil, M., Aly, M., Atiya, A.: ASTD: arabic sentiment tweets dataset. empirical methods in natural language processing, pp. 2515–2519 (2015)

    Google Scholar 

  33. ElSahar, H., El-Beltagy, S.R.: Building large arabic multi-domain resources for sentiment analysis. In: Gelbukh, A. (ed.) CICLing 2015. LNCS, vol. 9042, pp. 23–34. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-18117-2_2

    Chapter  Google Scholar 

  34. Steven, B., Loper, E., Klein, E.: Natural Language Processing with Python. O’Reilly Media Inc. (2009)

    Google Scholar 

  35. Chollet, F., et al.: Keras. GitHub. https://github.com/fchollet/keras (2015)

  36. Abadi, M., et al.: TensorFlow: Large-scale machine learning on heterogeneous systems. https://www.tensorflow.org/ (2015)

  37. Pedregosa, F., et al.: Scikit-learn: machine learning in Python. J. Mach. Learn. Res. 12, 2825–2830 (2011)

    MathSciNet  MATH  Google Scholar 

Download references

Acknowledgments

The research leading to the recorded results achievements has received funding from the Ministry of Higher Education and Scientific Research of Tunisia, under grant agreement number: LR11ES48.

Author information

Authors and Affiliations

  1. University of Sousse, 4011, ISITComSousse, Tunisia

    Mariem Abbes

  2. REGIM-Lab.: Research Groups on Intelligent Machines, University of Sfax, National Engineering School of Sfax (ENIS), BP1173, 3038, Sfax, Tunisia

    Mariem Abbes, Zied Kechaou & Adel M. Alimi

  3. Higher Business School of Sfax (ESCS), University of Sfax, Sfax, Tunisia

    Zied Kechaou

  4. Department of Electrical and Electronic Engineering Science Faculty of Engineering and the Built Environment, University of Johannesburg, Johannesburg, South Africa

    Adel M. Alimi

Authors
  1. Mariem Abbes
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Zied Kechaou
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Adel M. Alimi
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Mariem Abbes .

Editor information

Editors and Affiliations

  1. Department of Information and Communication Engineering, Fukuoka Institute of Technology, Fukuoka, Japan

    Leonard Barolli

Rights and permissions

Reprints and permissions

Copyright information

© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Abbes, M., Kechaou, Z., Alimi, A.M. (2023). A Novel Hybrid Model Based on CNN and Bi-LSTM for Arabic Multi-domain Sentiment Analysis. In: Barolli, L. (eds) Complex, Intelligent and Software Intensive Systems. CISIS 2023. Lecture Notes on Data Engineering and Communications Technologies, vol 176. Springer, Cham. https://doi.org/10.1007/978-3-031-35734-3_10

Download citation

Publish with us

Policies and ethics

Search

Navigation