Advertisement

Unsupervised User Behavior Representation for Fraud Review Detection with Cold-Start Problem

  • Qian LiEmail author
  • Qiang Wu
  • Chengzhang Zhu
  • Jian Zhang
  • Wentao Zhao
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11439)

Abstract

Detecting fraud review is becoming extremely important in order to provide reliable information in cyberspace, in which, however, handling cold-start problem is a critical and urgent challenge since the case of cold-start fraud review rarely provides sufficient information for further assessing its authenticity. Existing work on detecting cold-start cases relies on the limited contents of the review posted by the user and a traditional classifier to make the decision. However, simply modeling review is not reliable since reviews can be easily manipulated. Also, it is hard to obtain high-quality labeled data for training the classifier. In this paper, we tackle cold-start problems by (1) using a user’s behavior representation rather than review contents to measure authenticity, which further (2) consider user social relations with other existing users when posting reviews. The method is completely (3) unsupervised. Comprehensive experiments on Yelp data sets demonstrate our method significantly outperforms the state-of-the-art methods.

Keywords

Fraud review detection Cold-start Behavior representation Unsupervised learning 

References

  1. 1.
    Chen, J., Saad, Y.: Dense subgraph extraction with application to community detection. TKDE 24(7), 1216–1230 (2012)Google Scholar
  2. 2.
    Choo, E., Yu, T., Chi, M.: Detecting opinion spammer groups through community discovery and sentiment analysis. In: Samarati, P. (ed.) DBSec 2015. LNCS, vol. 9149, pp. 170–187. Springer, Cham (2015).  https://doi.org/10.1007/978-3-319-20810-7_11CrossRefGoogle Scholar
  3. 3.
    Fei, G., Mukherjee, A., Liu, B., Hsu, M., Castellanos, M., Ghosh, R.: Exploiting burstiness in reviews for review spammer detection. In: ICWSM 2013, pp. 175–184 (2013)Google Scholar
  4. 4.
    Feng, S., Xing, L., Gogar, A., Choi, Y.: Distributional footprints of deceptive product reviews. In: ICWSM 2012, pp. 98–105 (2012)Google Scholar
  5. 5.
    Hooi, B., Shin, K., Song, H.A., Beutel, A., Shah, N., Faloutsos, C.: Graph-based fraud detection in the face of camouflage. TKDD 11(4), 44 (2017)CrossRefGoogle Scholar
  6. 6.
    Hooi, B., Song, H.A., Beutel, A., Shah, N., Shin, K., Faloutsos, C.: FRAUDAR: bounding graph fraud in the face of camouflage. In: ACM SIGKDD, pp. 895–904. ACM (2016)Google Scholar
  7. 7.
    Hovy, D.: The enemy in your own camp: how well can we detect statistically-generated fake reviews-an adversarial study. In: ACL, vol. 2, pp. 351–356 (2016)Google Scholar
  8. 8.
    Jindal, N., Liu, B.: Opinion spam and analysis. In: WSDM, pp. 219–230. ACM (2008)Google Scholar
  9. 9.
    Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)
  10. 10.
    Li, H., Chen, Z., Liu, B., Wei, X., Shao, J.: Spotting fake reviews via collective positive-unlabeled learning. In: ICDM, pp. 899–904. IEEE (2014)Google Scholar
  11. 11.
    Li, H., Chen, Z., Mukherjee, A., Liu, B., Shao, J.: Analyzing and detecting opinion spam on a large-scale dataset via temporal and spatial patterns. In: ICWSM, pp. 634–637 (2015)Google Scholar
  12. 12.
    Li, H., et al.: Modeling review spam using temporal patterns and co-bursting behaviors. arXiv preprint arXiv:1611.06625 (2016)
  13. 13.
    Liu, S., Hooi, B., Faloutsos, C.: HoloScope: topology-and-spike aware fraud detection. In: CIKM, pp. 1539–1548. ACM (2017)Google Scholar
  14. 14.
    Luca, M., Zervas, G.: Fake it till you make it: reputation, competition, and yelp review fraud. Manag. Sci. 62(12), 3412–3427 (2016)CrossRefGoogle Scholar
  15. 15.
    van der Maaten, L., Hinton, G.: Visualizing data using t-SNE. JMLR 9(Nov), 2579–2605 (2008)zbMATHGoogle Scholar
  16. 16.
    Mukherjee, A., et al.: Spotting opinion spammers using behavioral footprints. In: ACM SIGKDD, pp. 632–640. ACM (2013)Google Scholar
  17. 17.
    Mukherjee, A., Liu, B., Wang, J., Glance, N., Jindal, N.: Detecting group review spam. In: WWW, pp. 93–94. ACM (2011)Google Scholar
  18. 18.
    Mukherjee, A., Venkataraman, V., Liu, B., Glance, N.: Fake review detection: classification and analysis of real and pseudo reviews. Technical report UIC-CS-2013-03, University of Illinois at Chicago (2013)Google Scholar
  19. 19.
    Mukherjee, A., Venkataraman, V., Liu, B., Glance, N.S.: What yelp fake review filter might be doing? In: ICWSM (2013)Google Scholar
  20. 20.
    Ott, M., Choi, Y., Cardie, C., Hancock, J.T.: Finding deceptive opinion spam by any stretch of the imagination. In: ACL HLT, pp. 309–319. Association for Computational Linguistics (2011)Google Scholar
  21. 21.
    Pennington, J., Socher, R., Manning, C.: GloVe: global vectors for word representation. In: EMNLP, pp. 1532–1543 (2014)Google Scholar
  22. 22.
    Rayana, S., Akoglu, L.: Collective opinion spam detection: bridging review networks and metadata. In: ACM SIGKDD, pp. 985–994. ACM (2015)Google Scholar
  23. 23.
    Rayana, S., Akoglu, L.: Collective opinion spam detection using active inference. In: ICDM, pp. 630–638. SIAM (2016)Google Scholar
  24. 24.
    Wang, G., Xie, S., Liu, B., Philip, S.Y.: Review graph based online store review spammer detection. In: ICDM, pp. 1242–1247. IEEE (2011)Google Scholar
  25. 25.
    Wang, X., Liu, K., Zhao, J.: Handling cold-start problem in review spam detection by jointly embedding texts and behaviors. In: ACL, vol. 1, pp. 366–376 (2017)Google Scholar
  26. 26.
    Wu, L., Hu, X., Morstatter, F., Liu, H.: Adaptive spammer detection with sparse group modeling. In: ICWSM, pp. 319–326 (2017)Google Scholar
  27. 27.
    Ye, J., Akoglu, L.: Discovering opinion spammer groups by network footprints. In: Appice, A., Rodrigues, P.P., Santos Costa, V., Soares, C., Gama, J., Jorge, A. (eds.) ECML PKDD 2015. LNCS (LNAI), vol. 9284, pp. 267–282. Springer, Cham (2015).  https://doi.org/10.1007/978-3-319-23528-8_17CrossRefGoogle Scholar
  28. 28.
    You, Z., Qian, T., Liu, B.: An attribute enhanced domain adaptive model for cold-start spam review detection. In: COLING, pp. 1884–1895 (2018)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Qian Li
    • 1
    Email author
  • Qiang Wu
    • 1
  • Chengzhang Zhu
    • 2
    • 3
  • Jian Zhang
    • 1
  • Wentao Zhao
    • 3
  1. 1.Global Big Data Technologies CentreUniversity of Technology SydneyUltimoAustralia
  2. 2.Advanced Analytics InstituteUniversity of Technology SydneyUltimoAustralia
  3. 3.College of ComputerNational University of Defense TechnologyChangshaChina

Personalised recommendations