Finding advertising keywords on web pages. Yih, W., Goodman, J., & Carvalho, V., R. Proceedings of the 15th international conference on World Wide Web WWW 06, ACM Press, 2006.
Finding advertising keywords on web pages [link]Website  abstract   bibtex   
A large and growing number of web pages display contex- tual advertising based on keywords automatically extracted from the text of the page, and this is a substantial source of revenue supporting the web today. Despite the impor- tance of this area, little formal, published research exists. We describe a system that learns how to extract keywords from web pages for advertisement targeting. The system uses a number of features, such as term frequency of each potential keyword, inverse document frequency, presence in meta-data, and how often the term occurs in search query logs. The system is trained with a set of example pages that have been hand-labeled with relevant keywords. Based on this training, it can then extract new keywords from previ- ously unseen pages. Accuracy is substantially better than several baseline systems.
@article{
 title = {Finding advertising keywords on web pages},
 type = {article},
 year = {2006},
 identifiers = {[object Object]},
 keywords = {advertising,information extraction,keyword extraction},
 pages = {213},
 websites = {http://portal.acm.org/citation.cfm?doid=1135777.1135813},
 publisher = {ACM Press},
 id = {e4cd287e-f720-3078-b2c3-3e174845b459},
 created = {2011-02-27T18:33:21.000Z},
 file_attached = {false},
 profile_id = {5284e6aa-156c-3ce5-bc0e-b80cf09f3ef6},
 group_id = {066b42c8-f712-3fc3-abb2-225c158d2704},
 last_modified = {2017-03-14T14:36:19.698Z},
 read = {false},
 starred = {false},
 authored = {false},
 confirmed = {true},
 hidden = {false},
 citation_key = {Yih2006},
 private_publication = {false},
 abstract = {A large and growing number of web pages display contex- tual advertising based on keywords automatically extracted from the text of the page, and this is a substantial source of revenue supporting the web today. Despite the impor- tance of this area, little formal, published research exists. We describe a system that learns how to extract keywords from web pages for advertisement targeting. The system uses a number of features, such as term frequency of each potential keyword, inverse document frequency, presence in meta-data, and how often the term occurs in search query logs. The system is trained with a set of example pages that have been hand-labeled with relevant keywords. Based on this training, it can then extract new keywords from previ- ously unseen pages. Accuracy is substantially better than several baseline systems.},
 bibtype = {article},
 author = {Yih, Wen-Tau and Goodman, Joshua and Carvalho, Vitor R},
 journal = {Proceedings of the 15th international conference on World Wide Web WWW 06}
}

Downloads: 0