An Empirical Study on the Change of Web Pages Export

@incollection{Kim05, abstract = {As web pages are created, destroyed, and updated dynamically, web databases should be frequently updated to keep web pages up-to-date. Understanding the change behavior of web pages certainly helps the administrators manage their web databases. This paper introduces a number of metrics representing various change behavior of the web pages. We have monitored approximately 1.8 million to three million URLs at two-day intervals for 100 days. Using the metrics we propose, we analyze the collected URLs and web pages. In addition, we propose a method that computes the probability that a page will be downloaded on the next crawls.}, author = {Kim, Sung J. and Lee, Sang H.}, booktitle = {Web Technologies Research and Development - APWeb 2005}, citeulike-article-id = {5860143}, citeulike-linkout-0 = {http://www.springerlink.com/content/pke67f19bgqpwn5m}, citeulike-linkout-1 = {http://dx.doi.org/10.1007/b106936}, doi = {10.1007/b106936}, journal = {Web Technologies Research and Development - APWeb 2005}, keywords = {characterization, dynamics, prodei, related, web}, pages = {632--642}, posted-at = {2009-09-30 15:56:04}, priority = {5}, publisher = {Springer Berlin / Heidelberg}, title = {An Empirical Study on the Change of Web Pages}, url = {http://dx.doi.org/10.1007/b106936}, year = {2005} }

TY - CHAP ID - Kim05 L3 - citeulike-article-id:5860143 N2 - As web pages are created, destroyed, and updated dynamically, web databases should be frequently updated to keep web pages up-to-date. Understanding the change behavior of web pages certainly helps the administrators manage their web databases. This paper introduces a number of metrics representing various change behavior of the web pages. We have monitored approximately 1.8 million to three million URLs at two-day intervals for 100 days. Using the metrics we propose, we analyze the collected URLs and web pages. In addition, we propose a method that computes the probability that a page will be downloaded on the next crawls. JF - Web Technologies Research and Development - APWeb 2005 EP - 642 TI - An Empirical Study on the Change of Web Pages PB - Springer Berlin / Heidelberg T2 - Web Technologies Research and Development - APWeb 2005 SP - 632 KW - characterization KW - dynamics KW - prodei KW - related KW - web AU - Kim, Sung AU - Lee, Sang PY - 2005/// UR - http://dx.doi.org/10.1007/b106936 ER -