%0 Conference Paper %1 Toyoda:2006:WRN:1135777.1135815 %A Toyoda, Masashi %A Kitsuregawa, Masaru %B Proceedings of the 15th International Conference on World Wide Web %C New York, NY, USA %D 2006 %I ACM %K web %P 233--241 %R 10.1145/1135777.1135815 %T What's Really New on the Web?: Identifying New Pages from a Series of Unstable Web Snapshots %U http://doi.acm.org/10.1145/1135777.1135815 %X Identifying and tracking new information on the Web is important in sociology, marketing, and survey research, since new trends might be apparent in the new information. Such changes can be observed by crawling the Web periodically. In practice, however, it is impossible to crawl the entire expanding Web repeatedly. This means that the novelty of a page remains unknown, even if that page did not exist in previous snapshots. In this paper, we propose a novelty measure for estimating the certainty that a newly crawled page appeared between the previous and current crawls. Using this novelty measure, new pages can be extracted from a series of unstable snapshots for further analysis and mining to identify new trends on the Web. We evaluated the precision, recall, and miss rate of the novelty measure using our Japanese web archive, and applied it to a Web archive search engine. %@ 1-59593-323-9

@inproceedings{Toyoda:2006:WRN:1135777.1135815, abstract = {Identifying and tracking new information on the Web is important in sociology, marketing, and survey research, since new trends might be apparent in the new information. Such changes can be observed by crawling the Web periodically. In practice, however, it is impossible to crawl the entire expanding Web repeatedly. This means that the novelty of a page remains unknown, even if that page did not exist in previous snapshots. In this paper, we propose a novelty measure for estimating the certainty that a newly crawled page appeared between the previous and current crawls. Using this novelty measure, new pages can be extracted from a series of unstable snapshots for further analysis and mining to identify new trends on the Web. We evaluated the precision, recall, and miss rate of the novelty measure using our Japanese web archive, and applied it to a Web archive search engine.}, acmid = {1135815}, added-at = {2023-06-09T10:41:43.000+0200}, address = {New York, NY, USA}, author = {Toyoda, Masashi and Kitsuregawa, Masaru}, biburl = {https://www.bibsonomy.org/bibtex/2cb3f2650462d64e574c324b9aebd3768/tobias.koopmann}, booktitle = {Proceedings of the 15th International Conference on World Wide Web}, doi = {10.1145/1135777.1135815}, interhash = {eb071377cdbb970f9857bac96a82bcc6}, intrahash = {cb3f2650462d64e574c324b9aebd3768}, isbn = {1-59593-323-9}, keywords = {web}, location = {Edinburgh, Scotland}, numpages = {9}, pages = {233--241}, publisher = {ACM}, series = {WWW '06}, timestamp = {2023-06-09T10:43:32.000+0200}, title = {What's Really New on the Web?: Identifying New Pages from a Series of Unstable Web Snapshots}, url = {http://doi.acm.org/10.1145/1135777.1135815}, year = 2006 }