Advertisement

Gender Prediction Through Synthetic Resampling of User Profiles Using SeqGANs

  • Munira Syed
  • Jermaine Marshall
  • Aastha Nigam
  • Nitesh V. ChawlaEmail author
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11917)

Abstract

Generative Adversarial Networks (GANs) have enabled researchers to achieve groundbreaking results on generating synthetic images. While GANs have been heavily used for generating synthetic image data, there is limited work on using GANs for synthetically resampling the minority class, particularly for text data. In this paper, we utilize Sequential Generative Adversarial Networks (SeqGAN) for creating synthetic user profiles from text data. The text data consists of articles that the users have read that are representative of the minority class. Our goal is to improve the predictive power of supervised learning algorithms for the gender prediction problem, using articles consumed by the user from a large health-based website as our data source. Our study shows that by creating synthetic user profiles for the minority class with SeqGANs and passing in the resampled training data to an XGBoost classifier, we achieve a gain of 2% in AUROC, as well as a 3% gain in both F1-Score and AUPR for gender prediction when compared to SMOTE. This is promising for the use of GANs in the application of text resampling.

Keywords

Gender prediction Resampling Adversarial Topic modeling 

Notes

Acknowledgements

We thank Trenton Ford for helpful discussions. This work was supported in part by the National Science Foundation (NSF) Grant IIS-1447795.

References

  1. 1.
    Anand, A., Gorde, K., Moniz, J.R.A., Park, N., Chakraborty, T., Chu, B.T.: Phishing URL detection with oversampling based on text generative adversarial networks. In: 2018 IEEE International Conference on Big Data (Big Data), pp. 1168–1177. IEEE (2018)Google Scholar
  2. 2.
    Bartoli, A., De Lorenzo, A., Medvet, E., Tarlao, F.: Your paper has been accepted, rejected, or whatever: automatic generation of scientific paper reviews. In: Buccafurri, F., Holzinger, A., Kieseberg, P., Tjoa, A.M., Weippl, E. (eds.) CD-ARES 2016. LNCS, vol. 9817, pp. 19–28. Springer, Cham (2016).  https://doi.org/10.1007/978-3-319-45507-5_2CrossRefGoogle Scholar
  3. 3.
    Barua, S., Islam, M.M., Murase, K.: ProWSyn: proximity weighted synthetic oversampling technique for imbalanced data set learning. In: Pei, J., Tseng, V.S., Cao, L., Motoda, H., Xu, G. (eds.) PAKDD 2013. LNCS (LNAI), vol. 7819, pp. 317–328. Springer, Heidelberg (2013).  https://doi.org/10.1007/978-3-642-37456-2_27CrossRefGoogle Scholar
  4. 4.
    Batista, G.E.A.P.A., Prati, R.C., Monard, M.C.: A study of the behavior of several methods for balancing machine learning training data. SIGKDD Explor. 6, 20–29 (2004)CrossRefGoogle Scholar
  5. 5.
    Chawla, N.V., Bowyer, K.W., Hall, L.O., Kegelmeyer, W.P.: SMOTE: synthetic minority over-sampling technique. J. Artif. Intell. Res. 16, 321–357 (2002)CrossRefGoogle Scholar
  6. 6.
    Chen, E., Lin, Y., Xiong, H., Luo, Q., Ma, H.: Exploiting probabilistic topic models to improve text categorization under class imbalance. Inf. Process. Manage. 47(2), 202–214 (2011)CrossRefGoogle Scholar
  7. 7.
    Chen, T., Guestrin, C.: XGBoost: a scalable tree boosting system. In: KDD (2016)Google Scholar
  8. 8.
    Fernández, A.: SMOTE for learning from imbalanced data: progress and challenges, marking the 15-year anniversary. J. Artif. Intell. Res. 61, 863–905 (2018)MathSciNetCrossRefGoogle Scholar
  9. 9.
    Hu, J., Zeng, H.J., Li, H., Niu, C., Chen, Z.: Demographic prediction based on user’s browsing behavior. In: WWW (2007)Google Scholar
  10. 10.
    Jindal, R., Malhotra, R., Jain, A.: Techniques for text classification: literature review and current trends. Webology 12(2), 1–28 (2015)Google Scholar
  11. 11.
    Kabbur, S., Han, E.H., Karypis, G.: Content-based methods for predicting web-site demographic attributes. In: 2010 IEEE International Conference on Data Mining, pp. 863–868 (2010) Google Scholar
  12. 12.
    Kim, D.Y., Lehto, X.Y., Morrison, A.M.: Gender differences in online travel information search: implications for marketing communications on the internet. Tourism Manage. 28(2), 423–433 (2007)CrossRefGoogle Scholar
  13. 13.
    Koto, F.: SMOTE-Out, SMOTE-Cosine, and Selected-SMOTE: an ehancement strategy to handle imbalance in data level. In: 2014 International Conference on Advanced Computer Science and Information System, pp. 280–284 (2014)Google Scholar
  14. 14.
    Lee, S.K., Hong, S.J., Yang, S.I.: Oversampling for imbalanced data classification using adversarial network. In: 2018 International Conference on Information and Communication Technology Convergence (ICTC), pp. 1255–1257. IEEE (2018)Google Scholar
  15. 15.
    McMahan, C., Hovland, R., McMillan, S.: Online marketing communications: exploring online consumer behavior by examining gender differences and interactivity within internet advertising. J. Interact. Advertising 10(1), 61–76 (2009)CrossRefGoogle Scholar
  16. 16.
    Nigam, A., Johnson, R.A., Wang, D., Chawla, N.V.: Characterizing online health and wellness information consumption: a study. Inf. Fusion 46, 33–43 (2019)CrossRefGoogle Scholar
  17. 17.
    Pedregosa, F., et al.: Scikit-learn: machine learning in Python. J. Mach. Learn. Res. 12, 2825–2830 (2011)MathSciNetzbMATHGoogle Scholar
  18. 18.
    Phuong, T.M., et al.: Gender prediction using browsing history. In: Huynh, V., Denoeux, T., Tran, D., Le, A., Pham, S. (eds.) Knowledge and Systems Engineering, pp. 271–283. Springer, Cham (2014).  https://doi.org/10.1007/978-3-319-02741-8_24CrossRefGoogle Scholar
  19. 19.
    Potash, P., Romanov, A., Rumshisky, A.: Ghostwriter: using an LSTM for automatic rap lyric generation. In: Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, pp. 1919–1924 (2015)Google Scholar
  20. 20.
    Sun, A., Lim, E.P., Liu, Y.: On strategies for imbalanced text classification using SVM: a comparative study. Decis. Support Syst. 48(1), 191–201 (2009)CrossRefGoogle Scholar
  21. 21.
    Yu, L., Zhang, W., Wang, J., Yu, Y.: SeqGAN: sequence generative adversarial nets with policy gradient. In: Thirty-First AAAI Conference on Artificial Intelligence (2017)Google Scholar
  22. 22.
    Zhu, X., Liu, Y., Qin, Z., Li, J.: Data Augmentation in Emotion Classification Using Generative Adversarial Networks. ArXiv abs/1711.00648 (2017)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Munira Syed
    • 1
  • Jermaine Marshall
    • 1
  • Aastha Nigam
    • 1
  • Nitesh V. Chawla
    • 1
    Email author
  1. 1.University of Notre DameNotre DameUSA

Personalised recommendations