We address the problem of identifying in app user actions from Web access logs when the content of those logs is both encrypted (through HTTPS) and also contains auto mated Web accesses. We nd that the distribution of time gaps between HTTPS accesses can distinguish user actions from automated Web accesses generated by the apps, and we determine that it is reasonable to identify meaningful user actions within mobile We blogs by modelling this temporal feature. A real-world experiment is conducted with multiple mobile devices running some popular apps , and the results show that the proposed clustering based method achieves good accuracy in identifying user actions , and outperformsthestate-of-the-artbaselineby17:84%.
@inproceedings{priyogi2018identifying,
author = {Priyogi, Bilih and Sanderson, Mark and Salim, Flora and Chan, Jeffrey and Tomko, Martin and Ren, Yongli},
booktitle = {Pacific-Asia Conference on Knowledge Discovery and Data Mining},
organization = {Springer},
pages = {300--311},
title = {Identifying In-App User Actions from Mobile Web Logs},
year = {2018}
}
© 2021 Flora Salim - CRUISE Research Group.