Efficient overlap and content reuse detection in blogs and online news articles Export

@inproceedings{citeulike:4389868, abstract = {The use of blogs to track and comment on real world (political, news, entertainment) events is growing. Similarly, as more individuals start relying on the Web as their primary information source and as more traditional media outlets try reaching consumers through alternative venues, the number of news sites on the Web is also continuously increasing. Content-reuse, whether in the form of extensive quotations or content borrowing across media outlets, is very common in blogs and news entries outlets tracking the same real-world event. Knowledge about which web entries re-use content from which others can be an effective asset when organizing these entries for presentation. On the other hand, this knowledge is not cheap to acquire: considering the size of the related space web entries, it is essential that the techniques developed for identifying re-use are fast and scalable. Furthermore, the dynamic nature of blog and news entries necessitates incremental processing for reuse detection. In this paper, we develop a novel qSign algorithm that efficiently and effectively analyze the blogosphere for quotation and reuse identification. Experiment results show that with qSign processing time gains from 10X to 100X are possible while maintaining reuse detection rates of upto 90\%. Furthermore, processing time gains can be pushed multiple orders of magnitude (from 100X to 1000X) for 70\% recall.}, address = {New York, NY, USA}, author = {Kim, Jong W. and Candan, Sel\c{c}uk K. and Tatemura, Junichi}, booktitle = {WWW '09: Proceedings of the 18th international conference on World wide web}, citeulike-article-id = {4389868}, citeulike-linkout-0 = {http://portal.acm.org/citation.cfm?id=1526709.1526721}, citeulike-linkout-1 = {http://dx.doi.org/10.1145/1526709.1526721}, doi = {10.1145/1526709.1526721}, isbn = {978-1-60558-487-4}, keywords = {algorithms, blogs, similarity, text}, location = {Madrid, Spain}, pages = {81--90}, posted-at = {2009-04-24 10:23:26}, priority = {5}, publisher = {ACM}, title = {Efficient overlap and content reuse detection in blogs and online news articles}, url = {http://dx.doi.org/10.1145/1526709.1526721}, year = {2009} }

TY - CONF ID - citeulike:4389868 L3 - citeulike-article-id:4389868 N2 - The use of blogs to track and comment on real world (political, news, entertainment) events is growing. Similarly, as more individuals start relying on the Web as their primary information source and as more traditional media outlets try reaching consumers through alternative venues, the number of news sites on the Web is also continuously increasing. Content-reuse, whether in the form of extensive quotations or content borrowing across media outlets, is very common in blogs and news entries outlets tracking the same real-world event. Knowledge about which web entries re-use content from which others can be an effective asset when organizing these entries for presentation. On the other hand, this knowledge is not cheap to acquire: considering the size of the related space web entries, it is essential that the techniques developed for identifying re-use are fast and scalable. Furthermore, the dynamic nature of blog and news entries necessitates incremental processing for reuse detection. In this paper, we develop a novel qSign algorithm that efficiently and effectively analyze the blogosphere for quotation and reuse identification. Experiment results show that with qSign processing time gains from 10X to 100X are possible while maintaining reuse detection rates of upto 90%. Furthermore, processing time gains can be pushed multiple orders of magnitude (from 100X to 1000X) for 70% recall. CY - Madrid, Spain SN - 978-1-60558-487-4 AD - New York, NY, USA EP - 90 TI - Efficient overlap and content reuse detection in blogs and online news articles PB - ACM T2 - WWW '09: Proceedings of the 18th international conference on World wide web SP - 81 KW - algorithms KW - blogs KW - similarity KW - text AU - Kim, Jong AU - Candan, Sel\c{c}uk AU - Tatemura, Junichi PY - 2009/// UR - http://dx.doi.org/10.1145/1526709.1526721 ER -