Gender Identification: A Comparative Study of Deep Learning Architectures

  • Bsir BassemEmail author
  • Mounir Zrigui
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 941)


Author profiling, dating back to the earliest attempts at of analyzing quantitative text documents, is an extensivel-studied problem among NLP researchers. Because of its utility in crime, marketing and business. In this paper, three deep learning methods were evaluated for author profiling using tweets in Arabic language. The first method is based on a Convolutional Neural Network (CNN) model, while the second and third technique belongs to the family of Recurrent Neural Networks (RNN). The appropriate choice of some parameters, such as the number of amount of filters, training epochs, batch size, dropout and learning rate of Adam optimizer used in a RNN model is crucial in obtaining reliable results. The experimental findings of our comparative evaluation study demonstrate that GRU model outperforms LSTM and CNN models.


Gated recurrent units Epochs Batch size Dropout GRU LSTM neural network CNN Author profiling Gender identification Deep learning 


  1. Ayadi, R., Maraoui, M., Zrigui, M.: Intertextual distance for Arabic texts classification. In: International Conference for Internet Technology and Secured Transactions, ICITST 2009, pp. 1–6. IEEE, November 2009Google Scholar
  2. Amodei, D., Ananthanarayanan, S., Anubhai, R., Bai, J., Battenberg, E., Case, C., Chen, J.: Deep speech 2: end-to-end speech recognition in English and Mandarin. In: International Conference on Machine Learning, pp. 173–182, June 2016Google Scholar
  3. Bsir, B., Zrigui, M.: Bidirectional LSTM for author gender identification. In: Nguyen, N., Pimenidis, E., Khan, Z., Trawiński, B. (eds.) Computational Collective Intelligence, ICCCI 2018. Lecture Notes in Computer Science, vol. 11055. Springer, Cham (2018)Google Scholar
  4. Bsir, B., Zrigui, M.: Enhancing deep learning gender identification with gated recurrent units architecture in social text. Computación y Sistemas 22(3), 2018 (2018)CrossRefGoogle Scholar
  5. Clauset, A., Moore, C., Newman, M.E.: Hierarchical structure and the prediction of missing links in networks. Nature 453(7191), 98 (2008)CrossRefGoogle Scholar
  6. Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997)CrossRefGoogle Scholar
  7. Howard, J., Ruder, S.: Finetuned language models for text classification. CoRR, abs/1801.06146 (2018)Google Scholar
  8. Kalchbrenner, N., Grefenstette, E., Blunsom, P.: A convolutional neural network for modelling sentences. arXiv preprint arXiv:1404.2188 (2014)
  9. Kodiyan, D., et al.: Author profiling with bidirectional RNNs using attention with GRUs: notebook for PAN at CLEF 2017. In: CLEF 2017 Evaluation Labs and Workshop–Working Notes Papers, Dublin, Ireland, 11–14 September 2017 (2017)Google Scholar
  10. Werlen, L.M.: Statistical learning methods for profiling analysis. In: Proceedings of CLEF 2015 Evaluation Labs (2015)Google Scholar
  11. Mahmoud, A., Zrigui, M.: Semantic similarity analysis for paraphrase identification in Arabic texts. In: Proceedings of the 31st Pacific Asia Conference on Language, Information and Computation, pp. 274–281 (2017)Google Scholar
  12. Maraoui, M., Antoniadis, G., Zrigui, M.: Un système de génération automatique de dictionnaires étiquetés de l’arabe. CITALA 2007(18–19), 2007 (2007)Google Scholar
  13. Miao, Y., Yu, L., Blunsom, P.: Neural variational inference for text processing. In: International Conference on Machine Learning, pp. 1727–1736, June 2016Google Scholar
  14. Rangel, F., Rosso, P., Montes-y-Gómez, M., Potthast, M., Stein, B.: Overview of the 6th author profiling task at pan 2018: multimodal gender identification in Twitter. Working Notes Papers of the CLEF (2018)Google Scholar
  15. Ruder, S., Ghaffari, P., Breslin, J.G.: Character-level and multi-channel convolutional neural networks for large-scale authorship attribution. arXiv preprint arXiv:1609.06686 (2016)
  16. Sap, M., Park, G., Eichstaedt, J., Kern, M., Stillwell, D., Kosinski, M., Ungar, L., Schwartz, H.A.: Developing age and gender predictive lexica over social media. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 1146–1151 (2014)Google Scholar
  17. Schaetti, N., Savoy, J.: Comparison of neural models for gender profiling (2018)Google Scholar
  18. Malmasi, S., et al.: Discriminating between similar languages and arabic dialect identification: a report on the third DSL shared task. VarDial 3 (2016)Google Scholar
  19. Socher, R., Perelygin, A., Wu, J., Chuang, J., Manning, C.D., Ng, A., Potts, C.: Recursive deep models for semantic compositionality over a sentiment treebank. In: Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, pp. 1631–1642 (2013)Google Scholar
  20. Stamatatos, E., Rangel, F., Tschuggnall, M., Stein, B., Kestemont, M., Rosso, P., Potthast, M.: Overview of PAN 2018. In: International Conference of the Cross-Language Evaluation Forum for European Languages, pp. 267–285. Springer, Cham, September 2018Google Scholar
  21. Stout, L., Musters, R., Pool, C.: Author profiling based on text and images. In: Experimental IR Meets Multilinguality, Multimodality, and Interaction. Proceedings of the Ninth International Conference of the CLEF Association (CLEF 2018), September 2018Google Scholar
  22. Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2818–2826 (2016)Google Scholar
  23. Veenhoven, R., Snijders, S., van der Hall, D., van Noord, R.: Using translated data to improve deep learning author profiling models. In: Experimental IR Meets Multilinguality, Multimodality, and Interaction. Proceedings of the Ninth International Conference of the CLEF Association (CLEF 2018), September 2018Google Scholar
  24. Zhu, X., Sobihani, P., Guo, H.: Long short-term memory over recursive structures. In: International Conference on Machine Learning, pp. 1604–1612, June 2015Google Scholar
  25. Zrigui, M., Ayadi, R., Mars, M., Maraoui, M.: Arabic text classification framework based on latent dirichlet allocation. J. Comput. Inf. Technol. 20(2), 125–140 (2012)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  1. 1.LATICE Laboratory Research Department of Computer ScienceUniversity of MonastirMonastirTunisia

Personalised recommendations