Leveraging Analysis of User Behavior from Web Usage Extraction over DOM-tree Structure
Understanding the user behavior is paramount for the success of any website. Existing approaches for understanding the user behavior in web applications exploit server web logs. We advocate that collecting client web logs, which contain more detailed information regarding web elements at DOM-tree level, is more effective to understand the user behavior. As the volume of client log data is significantly larger than the volume of server logs, we propose a graph-based model that aims to represent client log data in such a way that makes it processing feasible. An experiment performed with a large volume of client web logs shows that our model is able to provide interesting insights regarding the user behavior in web applications.
KeywordsUser behavior Graph theory Web usage Pattern extraction
- 2.Liu, G., Nguyen, T.T., Zhao, G., Zha, W., Yang, J., Cao, J., Wu, M., Zhao, P., Chen, W.: Repeat buyer prediction for e-commerce. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD 2016, pp. 155–164. ACM, New York (2016)Google Scholar
- 4.Neelima, G., Rodda, S.: Predicting user behavior through sessions using the web log mining. In: 2016 International Conference on Advances in Human Machine Interaction (HMI), pp. 1–5, March 2016Google Scholar
- 5.Bernaschina, C., Brambilla, M., Mauri, A., Umuhoza, E.: A big data analysis framework for model-based web user behavior analytics. In: Cabot, J., De Virgilio, R., Torlone, R. (eds.) ICWE 2017. LNCS, vol. 10360, pp. 98–114. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-60131-1_6CrossRefGoogle Scholar
- 6.Hernandez, S., Alvarez, P., Fabra, J., Ezpeleta, J.: Analysis of users’ behaviour in structured e-commerce websites. IEEE Access PP(99), 1 (2017)Google Scholar