The web changes everything: understanding the dynamics of web content Export

@inproceedings{Adar09, abstract = {The Web is a dynamic, ever changing collection of information. This paper explores changes in Web content by analyzing a crawl of 55,000 Web pages, selected to represent different user visitation patterns. Although change over long intervals has been explored on random (and potentially unvisited) samples of Web pages, little is known about the nature of finer grained changes to pages that are actively consumed by users, such as those in our sample. We describe algorithms, analyses, and models for characterizing changes in Web content, focusing on both time (by using hourly and sub-hourly crawls) and structure (by looking at page-, DOM-, and term-level changes). Change rates are higher in our behavior-based sample than found in previous work on randomly sampled pages, with a large portion of pages changing more than hourly. Detailed content and structure analyses identify stable and dynamic content within each page. The understanding of Web change we develop in this paper has implications for tools designed to help people interact with dynamic Web content, such as search engines, advertising, and Web browsers.}, address = {New York, NY, USA}, author = {Adar, Eytan and Teevan, Jaime and Dumais, Susan T. and Elsas, Jonathan L.}, booktitle = {WSDM '09: Proceedings of the Second ACM International Conference on Web Search and Data Mining}, citeulike-article-id = {5859442}, citeulike-linkout-0 = {http://portal.acm.org/citation.cfm?id=1498837}, citeulike-linkout-1 = {http://dx.doi.org/10.1145/1498759.1498837}, doi = {10.1145/1498759.1498837}, isbn = {978-1-60558-390-7}, keywords = {characterization, dynamics, prodei, related, web}, location = {Barcelona, Spain}, pages = {282--291}, posted-at = {2009-09-30 12:19:42}, priority = {5}, publisher = {ACM}, title = {The web changes everything: understanding the dynamics of web content}, url = {http://dx.doi.org/10.1145/1498759.1498837}, year = {2009} }

TY - CONF ID - Adar09 L3 - citeulike-article-id:5859442 N2 - The Web is a dynamic, ever changing collection of information. This paper explores changes in Web content by analyzing a crawl of 55,000 Web pages, selected to represent different user visitation patterns. Although change over long intervals has been explored on random (and potentially unvisited) samples of Web pages, little is known about the nature of finer grained changes to pages that are actively consumed by users, such as those in our sample. We describe algorithms, analyses, and models for characterizing changes in Web content, focusing on both time (by using hourly and sub-hourly crawls) and structure (by looking at page-, DOM-, and term-level changes). Change rates are higher in our behavior-based sample than found in previous work on randomly sampled pages, with a large portion of pages changing more than hourly. Detailed content and structure analyses identify stable and dynamic content within each page. The understanding of Web change we develop in this paper has implications for tools designed to help people interact with dynamic Web content, such as search engines, advertising, and Web browsers. CY - Barcelona, Spain SN - 978-1-60558-390-7 AD - New York, NY, USA EP - 291 TI - The web changes everything: understanding the dynamics of web content PB - ACM T2 - WSDM '09: Proceedings of the Second ACM International Conference on Web Search and Data Mining SP - 282 KW - characterization KW - dynamics KW - prodei KW - related KW - web AU - Adar, Eytan AU - Teevan, Jaime AU - Dumais, Susan AU - Elsas, Jonathan PY - 2009/// UR - http://dx.doi.org/10.1145/1498759.1498837 ER -