A probabilistic approach to spatiotemporal theme pattern mining on weblogs Export

@inproceedings{citeulike:957631, abstract = {Mining subtopics from weblogs and analyzing their spatiotemporal patterns have applications in multiple domains. In this paper, we define the novel problem of mining spatiotemporal theme patterns from weblogs and propose a novel probabilistic approach to model the subtopic themes and spatiotemporal theme patterns simultaneously. The proposed model discovers spatiotemporal theme patterns by (1) extracting common themes from weblogs; (2) generating theme life cycles for each given location; and (3) generating theme snapshots for each given time period. Evolution of patterns can be discovered by comparative analysis of theme life cycles and theme snapshots. Experiments on three different data sets show that the proposed approach can discover interesting spatiotemporal theme patterns effectively. The proposed probabilistic model is general and can be used for spatiotemporal text mining on any domain with time and location information.}, address = {New York, NY, USA}, author = {Mei, Qiaozhu and Liu, Chao and Su, Hang and Zhai, ChengXiang}, booktitle = {WWW '06: Proceedings of the 15th international conference on World Wide Web}, citeulike-article-id = {957631}, citeulike-linkout-0 = {http://portal.acm.org/citation.cfm?id=1135777.1135857}, citeulike-linkout-1 = {http://dx.doi.org/10.1145/1135777.1135857}, doi = {10.1145/1135777.1135857}, isbn = {1-59593-323-9}, keywords = {mining, theme, weblog}, location = {Edinburgh, Scotland}, pages = {533--542}, posted-at = {2009-10-26 22:23:58}, priority = {2}, publisher = {ACM}, title = {A probabilistic approach to spatiotemporal theme pattern mining on weblogs}, url = {http://dx.doi.org/10.1145/1135777.1135857}, year = {2006} }

TY - CONF ID - citeulike:957631 L3 - citeulike-article-id:957631 N2 - Mining subtopics from weblogs and analyzing their spatiotemporal patterns have applications in multiple domains. In this paper, we define the novel problem of mining spatiotemporal theme patterns from weblogs and propose a novel probabilistic approach to model the subtopic themes and spatiotemporal theme patterns simultaneously. The proposed model discovers spatiotemporal theme patterns by (1) extracting common themes from weblogs; (2) generating theme life cycles for each given location; and (3) generating theme snapshots for each given time period. Evolution of patterns can be discovered by comparative analysis of theme life cycles and theme snapshots. Experiments on three different data sets show that the proposed approach can discover interesting spatiotemporal theme patterns effectively. The proposed probabilistic model is general and can be used for spatiotemporal text mining on any domain with time and location information. CY - Edinburgh, Scotland SN - 1-59593-323-9 AD - New York, NY, USA EP - 542 TI - A probabilistic approach to spatiotemporal theme pattern mining on weblogs PB - ACM T2 - WWW '06: Proceedings of the 15th international conference on World Wide Web SP - 533 KW - mining KW - theme KW - weblog AU - Mei, Qiaozhu AU - Liu, Chao AU - Su, Hang AU - Zhai, ChengXiang PY - 2006/// UR - http://dx.doi.org/10.1145/1135777.1135857 ER -