What's in a session: Tracking individual behavior on the web. Meiss, M., Duncan, J., Gonçalves, B., Ramasco, J., J., & Menczer, F. In Proceedings of the 20th ACM Conference on Hypertext and Hypermedia, HT'09, pages 173-182, 2009.
What's in a session: Tracking individual behavior on the web [link]Website  doi  abstract   bibtex   
We examine the properties of all HTTP requests generated by a thousand undergraduates over a span of two months. Preserving user identity in the data set allows us to discover novel properties of Web traffic that directly affect models of hypertext navigation. We find that the popularity of Web sites-the number of users who contribute to their traffic-lacks any intrinsic mean and may be unbounded. Further, many aspects of the browsing behavior of individual users can be approximated by log-normal distributions even though their aggregate behavior is scale-free. Finally, we show that users' click streams cannot be cleanly segmented into sessions using timeouts, affecting any attempt to model hypertext navigation using statistics of individual sessions. We propose a strictly logical definition of sessions based on browsing activity as revealed by referrer URLs; a user may have several active sessions in their click stream at any one time. We demonstrate that applying a timeout to these logical sessions affects their statistics to a lesser extent than a purely timeout-based mechanism. Copyright 2009 ACM.
@inproceedings{
 title = {What's in a session: Tracking individual behavior on the web},
 type = {inproceedings},
 year = {2009},
 keywords = {Aggregate behavior; Browsing behavior; Click strea,Hydraulics; Hypertext systems; Navigation; Normal,World Wide Web},
 pages = {173-182},
 websites = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-70450183880&doi=10.1145%2F1557914.1557946&partnerID=40&md5=c2383a5d1a1bed10c0a4e03009cb1f3a},
 city = {Torino},
 id = {b99faf48-f16f-311d-ad34-30c123216722},
 created = {2018-01-16T17:54:28.211Z},
 file_attached = {false},
 profile_id = {42d295c0-0737-38d6-8b43-508cab6ea85d},
 last_modified = {2018-03-12T19:03:19.433Z},
 read = {false},
 starred = {false},
 authored = {true},
 confirmed = {true},
 hidden = {false},
 citation_key = {Meiss2009173},
 source_type = {conference},
 notes = {cited By 21; Conference of 20th ACM Conference on Hypertext and Hypermedia, HT'09 ; Conference Date: 29 June 2009 Through 1 July 2009; Conference Code:77901},
 folder_uuids = {971e10ae-b1f7-4c4b-8f99-aa55f77a64f6},
 private_publication = {false},
 abstract = {We examine the properties of all HTTP requests generated by a thousand undergraduates over a span of two months. Preserving user identity in the data set allows us to discover novel properties of Web traffic that directly affect models of hypertext navigation. We find that the popularity of Web sites-the number of users who contribute to their traffic-lacks any intrinsic mean and may be unbounded. Further, many aspects of the browsing behavior of individual users can be approximated by log-normal distributions even though their aggregate behavior is scale-free. Finally, we show that users' click streams cannot be cleanly segmented into sessions using timeouts, affecting any attempt to model hypertext navigation using statistics of individual sessions. We propose a strictly logical definition of sessions based on browsing activity as revealed by referrer URLs; a user may have several active sessions in their click stream at any one time. We demonstrate that applying a timeout to these logical sessions affects their statistics to a lesser extent than a purely timeout-based mechanism. Copyright 2009 ACM.},
 bibtype = {inproceedings},
 author = {Meiss, M and Duncan, J and Gonçalves, B and Ramasco, J J and Menczer, F},
 doi = {10.1145/1557914.1557946},
 booktitle = {Proceedings of the 20th ACM Conference on Hypertext and Hypermedia, HT'09}
}

Downloads: 0