InnerBehavior: effective representation learning for web user behavior analysis

Internet surfing is one of the most frequent activities in our daily lives. Investigation of web user behaviors may help to disclose the Internet usage habits, the life-styles and even the personality of users. Previous studies on web user Behaviors mainly based on data collected from questionnaires or log files of a particular website and the extracted features are manually designed for a specific application. In this paper, we propose a two-stage feature extraction framework called "InnerBehavior", which aims to reconstruct a general representation for web user behaviors from millions of access records. The proposed framework is employed to the detection of Internet addiction users. Experiment results demonstrate the effectiveness of the framework.

[1]  Sireesha Rodda,et al.  Predicting user behavior through sessions using the web log mining , 2016, 2016 International Conference on Advances in Human Machine Interaction (HMI).

[2]  SERGIO HERNÁNDEZ,et al.  Analysis of users’ behaviour in structured e-commerce websites , 2017 .

[3]  K. Thangavel,et al.  Clustering Categorical Data Using Silhouette Coefficient as a Relocating Measure , 2007, International Conference on Computational Intelligence and Multimedia Applications (ICCIMA 2007).

[4]  Yan Tang,et al.  Research on Web Log Mining , 2013 .

[5]  Yinghui Yang,et al.  Web user behavioral profiling for user identification , 2010, Decis. Support Syst..

[6]  Zheng Yan,et al.  Self-Report Versus Web-Log: Which One is Better to Predict Personality of Website Users? , 2013, Int. J. Cyber Behav. Psychol. Learn..

[7]  Pablo E. Román,et al.  A Dynamic Stochastic Model Applied to the Analysis of the Web User Behavior , 2010 .

[8]  Yoshua Bengio,et al.  Greedy Layer-Wise Training of Deep Networks , 2006, NIPS.

[9]  Alireza Yari,et al.  N-gram based text classification for Persian newspaper corpus , 2011, The 7th International Conference on Digital Content, Multimedia Technology and its Applications.

[10]  Martin F. Arlitt,et al.  Characterizing Web user sessions , 2000, PERV.

[11]  Chang Zhou,et al.  ATRank: An Attention-Based User Behavior Modeling Framework for Recommendation , 2017, AAAI.

[12]  Danfeng Yao,et al.  DECT: Distributed Evolving Context Tree for Mining Web Behavior Evolution , 2016, EDBT.

[13]  L. Weng,et al.  Development of a Chinese Internet addiction scale and its psychometric study , 2003 .

[14]  Chandrabose Aravindan,et al.  Web page classification using n-gram based URL features , 2013, 2013 Fifth International Conference on Advanced Computing (ICoAC).

[15]  Oussama Metatla,et al.  Proceedings of the 2016 CHI Conference on Human Factors in Computing Systems , 2016 .

[16]  Dong-Il Kim,et al.  Epidemiology of Internet Behaviors and Addiction Among Adolescents in Six Asian Countries , 2014, Cyberpsychology Behav. Soc. Netw..

[17]  L. Weng,et al.  Chinese Internet Addiction Scale--Revised , 2016 .

[18]  Charu C. Aggarwal,et al.  You Are How You Drive: Peer and Temporal-Aware Representation Learning for Driving Behavior Analysis , 2018, KDD.

[19]  Monika Henzinger,et al.  Purely URL-based topic classification , 2009, WWW '09.

[20]  Gang Wang,et al.  Unsupervised Clickstream Clustering for User Behavior Analysis , 2016, CHI.