%0 Journal Article %1 Wang:2017:CUB:3127338.3068332 %A Wang, Gang %A Zhang, Xinyi %A Tang, Shiliang %A Wilson, Christo %A Zheng, Haitao %A Zhao, Ben Y. %C New York, NY, USA %D 2017 %I ACM %J ACM Trans. Web %K behavior clickstream %N 4 %P 21:1--21:37 %R 10.1145/3068332 %T Clickstream User Behavior Models %U http://doi.acm.org/10.1145/3068332 %V 11 %X The next generation of Internet services is driven by users and user-generated content. The complex nature of user behavior makes it highly challenging to manage and secure online services. On one hand, service providers cannot effectively prevent attackers from creating large numbers of fake identities to disseminate unwanted content (e.g., spam). On the other hand, abusive behavior from real users also poses significant threats (e.g., cyberbullying). In this article, we propose clickstream models to characterize user behavior in large online services. By analyzing clickstream traces (i.e., sequences of click events from users), we seek to achieve two goals: (1) detection: to capture distinct user groups for the detection of malicious accounts, and (2) understanding: to extract semantic information from user groups to understand the captured behavior. To achieve these goals, we build two related systems. The first one is a semisupervised system to detect malicious user accounts (Sybils). The core idea is to build a clickstream similarity graph where each node is a user and an edge captures the similarity of two users’ clickstreams. Based on this graph, we propose a coloring scheme to identify groups of malicious accounts without relying on a large labeled dataset. We validate the system using ground-truth clickstream traces of 16,000 real and Sybil users from Renren, a large Chinese social network. The second system is an unsupervised system that aims to capture and understand the fine-grained user behavior. Instead of binary classification (malicious or benign), this model identifies the natural groups of user behavior and automatically extracts features to interpret their semantic meanings. Applying this system to Renren and another online social network, Whisper (100K users), we help service providers identify unexpected user behaviors and even predict users’ future actions. Both systems received positive feedback from our industrial collaborators including Renren, LinkedIn, and Whisper after testing on their internal clickstream data.

@article{Wang:2017:CUB:3127338.3068332, abstract = {The next generation of Internet services is driven by users and user-generated content. The complex nature of user behavior makes it highly challenging to manage and secure online services. On one hand, service providers cannot effectively prevent attackers from creating large numbers of fake identities to disseminate unwanted content (e.g., spam). On the other hand, abusive behavior from real users also poses significant threats (e.g., cyberbullying). In this article, we propose clickstream models to characterize user behavior in large online services. By analyzing clickstream traces (i.e., sequences of click events from users), we seek to achieve two goals: (1) detection: to capture distinct user groups for the detection of malicious accounts, and (2) understanding: to extract semantic information from user groups to understand the captured behavior. To achieve these goals, we build two related systems. The first one is a semisupervised system to detect malicious user accounts (Sybils). The core idea is to build a clickstream similarity graph where each node is a user and an edge captures the similarity of two users’ clickstreams. Based on this graph, we propose a coloring scheme to identify groups of malicious accounts without relying on a large labeled dataset. We validate the system using ground-truth clickstream traces of 16,000 real and Sybil users from Renren, a large Chinese social network. The second system is an unsupervised system that aims to capture and understand the fine-grained user behavior. Instead of binary classification (malicious or benign), this model identifies the natural groups of user behavior and automatically extracts features to interpret their semantic meanings. Applying this system to Renren and another online social network, Whisper (100K users), we help service providers identify unexpected user behaviors and even predict users’ future actions. Both systems received positive feedback from our industrial collaborators including Renren, LinkedIn, and Whisper after testing on their internal clickstream data.}, acmid = {3068332}, added-at = {2018-09-16T14:40:24.000+0200}, address = {New York, NY, USA}, articleno = {21}, author = {Wang, Gang and Zhang, Xinyi and Tang, Shiliang and Wilson, Christo and Zheng, Haitao and Zhao, Ben Y.}, biburl = {https://www.bibsonomy.org/bibtex/221a2a38e4f1f5ed92295328ec4e023a6/e.fischer}, description = {Clickstream User Behavior Models}, doi = {10.1145/3068332}, interhash = {f6bc42b160d96e4a083660a3c3445b44}, intrahash = {21a2a38e4f1f5ed92295328ec4e023a6}, issn = {1559-1131}, issue_date = {September 2017}, journal = {ACM Trans. Web}, keywords = {behavior clickstream}, month = jul, number = 4, numpages = {37}, pages = {21:1--21:37}, publisher = {ACM}, timestamp = {2018-09-16T14:40:56.000+0200}, title = {Clickstream User Behavior Models}, url = {http://doi.acm.org/10.1145/3068332}, volume = 11, year = 2017 }