How to Verify Users via Web Behavior Features: Based on the Human Behavioral Theory

  • Jiajia Li
  • Qian YiEmail author
  • Shuping Yi
  • Shuping Xiong
  • Su Yang
Conference paper
Part of the Communications in Computer and Information Science book series (CCIS, volume 924)


Nowadays, the Internet has penetrated into people’s daily life in many ways, and people usually use the form of web account to carry out web activities. However, the problem of user account being illegally occupied by others has become increasingly prominent, and the security of user account is not guaranteed. On the other side, the network’s advantage of recording data easily provides a valuable opportunity to comprehensively record a tremendous amount of human behaviors. Based upon the status and problems, we present an approach to distinguish genuine account owners from intruders. This study constructs a series of web behavior features based on web usage logs, and uses machine learning to identify users based on Bayesian theorem and structural risk minimization criterion. Experiments show that web behavior analysis is a feasible way for user verification.


Human behavior Human web behavior User verification Machine learning 



This work was supported by Fundamental Research Funds for the Central Universities NO. 106112016CDJXY110003, 2016.1-2017.12 and the National Natural Science Foundation of China under Grant No. 71671020.


  1. 1.
    CNNIC: The thirty-ninth statistical report on the development of Internet in China (2017).
  2. 2.
    Géczy, P., Izumi, N., Akaho, S., et al.: Human behavior on web: what is known. In: International Proceedings of Economics Development & Research (2011)Google Scholar
  3. 3.
    Guo, J.L., Fan, C., Guo, Z.H.: Weblog patterns and human dynamics with decreasing interest. Eur. Phys. J. B 81(3), 341–344 (2011)CrossRefGoogle Scholar
  4. 4.
    Neelima, G., Rodda, S.: Predicting user behavior through sessions using the web log mining. In: International Conference on Advances in Human Machine Interaction, pp. 1–5. IEEE (2016)Google Scholar
  5. 5.
    Zhong, J., Yan, C., Yu, W., et al.: A kind of identity authentication method based on browsing behaviors. In: Seventh International Symposium on Computational Intelligence and Design, pp. 279–284. IEEE Computer Society (2014)Google Scholar
  6. 6.
    Leung, R., Law, R., Masiero, L., et al.: Behavior of online visitors to hotel ICON: a weekday-weekend analysis. e-Rev. Tour. Res. 7 (2016)Google Scholar
  7. 7.
    Cui, P., Liu, H., Aggarwal, C., et al.: Uncovering and predicting human behaviors. IEEE Intell. Syst. 31(2), 77–88 (2016)CrossRefGoogle Scholar
  8. 8.
    Lin, C.J., Wu, C., Chaovalitwongse, W.A.: Integrating human behavior modeling and data mining techniques to predict human errors in numerical typing. IEEE Trans. Hum.-Mach. Syst. 45(1), 39–50 (2017)CrossRefGoogle Scholar
  9. 9.
    Pennacchiotti, M., Popescu, A.M.: A machine learning approach to Twitter user classification. In: International Conference on Weblogs and Social Media, Barcelona, Catalonia, Spain. DBLP, July 2011Google Scholar
  10. 10.
    Feher, C.: User identity verification via mouse dynamics. Inf. Sci. 201(19), 19–36 (2012)CrossRefGoogle Scholar
  11. 11.
    Pao, H.K., Fadlil, J., Lin, H.Y., et al.: Trajectory analysis for user verification and recognition. Knowl.-Based Syst. 34(5), 81–90 (2012)CrossRefGoogle Scholar
  12. 12.
    Von Mises, L., Greaves, B.B.: Human Action: The Treatise on Economics. Liberty Fund, Carmel (2007)Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2018

Authors and Affiliations

  • Jiajia Li
    • 1
  • Qian Yi
    • 1
    Email author
  • Shuping Yi
    • 1
  • Shuping Xiong
    • 1
  • Su Yang
    • 1
  1. 1.College of Mechanical EngineeringChongqing UniversityChongqingChina

Personalised recommendations