{"id":"https://openalex.org/W2074316299","doi":"https://doi.org/10.1145/1135777.1135922","title":"Verifying genre-based clustering approach to content extraction","display_name":"Verifying genre-based clustering approach to content extraction","publication_year":2006,"publication_date":"2006-05-23","ids":{"openalex":"https://openalex.org/W2074316299","doi":"https://doi.org/10.1145/1135777.1135922","mag":"2074316299"},"language":"en","primary_location":{"id":"doi:10.1145/1135777.1135922","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1135777.1135922","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th international conference on World Wide Web","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5064707257","display_name":"Suhit Gupta","orcid":null},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Suhit Gupta","raw_affiliation_strings":["Columbia University, New York, NY","Columbia University, New York, NY;"],"affiliations":[{"raw_affiliation_string":"Columbia University, New York, NY","institution_ids":["https://openalex.org/I78577930"]},{"raw_affiliation_string":"Columbia University, New York, NY;","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111369403","display_name":"Hila Becker","orcid":null},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hila Becker","raw_affiliation_strings":["Columbia University, New York, NY","Columbia University, New York, NY;"],"affiliations":[{"raw_affiliation_string":"Columbia University, New York, NY","institution_ids":["https://openalex.org/I78577930"]},{"raw_affiliation_string":"Columbia University, New York, NY;","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090171418","display_name":"Gail E. Kaiser","orcid":"https://orcid.org/0000-0002-8791-1178"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gail Kaiser","raw_affiliation_strings":["Columbia University, New York, NY","Columbia University, New York, NY;"],"affiliations":[{"raw_affiliation_string":"Columbia University, New York, NY","institution_ids":["https://openalex.org/I78577930"]},{"raw_affiliation_string":"Columbia University, New York, NY;","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084213178","display_name":"Salvatore J. Stolfo","orcid":"https://orcid.org/0000-0003-1611-0100"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Salvatore Stolfo","raw_affiliation_strings":["Columbia University, New York, NY","Columbia University, New York, NY;"],"affiliations":[{"raw_affiliation_string":"Columbia University, New York, NY","institution_ids":["https://openalex.org/I78577930"]},{"raw_affiliation_string":"Columbia University, New York, NY;","institution_ids":["https://openalex.org/I78577930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5064707257"],"corresponding_institution_ids":["https://openalex.org/I78577930"],"apc_list":null,"apc_paid":null,"fwci":5.1712,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.95019515,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"875","last_page":"876"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9869999885559082,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12720","display_name":"Multimedia Communication and Technology","score":0.961899995803833,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7997642755508423},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.7963703870773315},{"id":"https://openalex.org/keywords/rendering","display_name":"Rendering (computer graphics)","score":0.634384036064148},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6230402588844299},{"id":"https://openalex.org/keywords/clutter","display_name":"Clutter","score":0.6087446808815002},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.43012842535972595},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3473805785179138},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.2818302810192108},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.18295583128929138},{"id":"https://openalex.org/keywords/radar","display_name":"Radar","score":0.1424207091331482}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7997642755508423},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.7963703870773315},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.634384036064148},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6230402588844299},{"id":"https://openalex.org/C132094186","wikidata":"https://www.wikidata.org/wiki/Q641585","display_name":"Clutter","level":3,"score":0.6087446808815002},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.43012842535972595},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3473805785179138},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.2818302810192108},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.18295583128929138},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.1424207091331482},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1135777.1135922","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1135777.1135922","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th international conference on World Wide Web","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.76.6423","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.76.6423","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www2006.org/programme/files/pdf/p88.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.5699999928474426}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":3,"referenced_works":["https://openalex.org/W102858063","https://openalex.org/W2012575882","https://openalex.org/W4255664058"],"related_works":["https://openalex.org/W2130674020","https://openalex.org/W2093748878","https://openalex.org/W2333771223","https://openalex.org/W2120056845","https://openalex.org/W1981531423","https://openalex.org/W4394861761","https://openalex.org/W1977371217","https://openalex.org/W2035264131","https://openalex.org/W1679012645","https://openalex.org/W2000745862"],"abstract_inverted_index":{"The":[0],"content":[1,26],"of":[2,12,52,58,97],"a":[3,9,59,65,77,95],"webpage":[4],"is":[5],"usually":[6],"contained":[7],"within":[8],"small":[10,38],"body":[11],"text":[13],"and":[14,41,44,72,109],"images,":[15],"or":[16],"perhaps":[17],"several":[18],"articles":[19],"on":[20,37,49],"the":[21,25,31,56,85,88,106],"same":[22],"page;":[23],"however,":[24],"may":[27],"be":[28],"lost":[29],"in":[30,87],"clutter,":[32],"particularly":[33],"hurting":[34],"users":[35,47],"browsing":[36],"cell":[39],"phone":[40],"PDA":[42],"screens":[43],"visually":[45],"impaired":[46],"relying":[48],"speed":[50],"rendering":[51],"web":[53,60],"pages.":[54],"Using":[55],"genre":[57],"page,":[61],"we":[62,93,102],"have":[63,103],"created":[64],"solution,":[66],"Crunch":[67],"that":[68],"automatically":[69],"identifies":[70],"clutter":[71],"removes":[73],"it,":[74],"thus":[75],"leaving":[76],"clean":[78],"content-full":[79],"page.":[80],"In":[81,99],"order":[82],"to":[83],"evaluate":[84],"improvement":[86],"applications":[89],"for":[90],"this":[91,100],"technology,":[92],"identified":[94],"number":[96],"experiments.":[98],"paper,":[101],"those":[104],"experiments,":[105],"associated":[107],"results":[108],"their":[110],"evaluation.":[111]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
