{"id":"https://openalex.org/W2040075907","doi":"https://doi.org/10.1145/511446.511522","title":"Template detection via data mining and its applications","display_name":"Template detection via data mining and its applications","publication_year":2002,"publication_date":"2002-05-07","ids":{"openalex":"https://openalex.org/W2040075907","doi":"https://doi.org/10.1145/511446.511522","mag":"2040075907"},"language":"en","primary_location":{"id":"doi:10.1145/511446.511522","is_oa":false,"landing_page_url":"https://doi.org/10.1145/511446.511522","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 11th 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/A5054834255","display_name":"Ziv Bar-Yossef","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ziv Bar-Yossef","raw_affiliation_strings":["University of California at Berkeley, Berkeley, CA"],"affiliations":[{"raw_affiliation_string":"University of California at Berkeley, Berkeley, CA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5104023644","display_name":"Sridhar Rajagopalan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sridhar Rajagopalan","raw_affiliation_strings":["IBM Almaden Research Center, San Jose, CA","IBM Almaden Research Center San Jose , CA"],"affiliations":[{"raw_affiliation_string":"IBM Almaden Research Center, San Jose, CA","institution_ids":["https://openalex.org/I4210085935"]},{"raw_affiliation_string":"IBM Almaden Research Center San Jose , CA","institution_ids":["https://openalex.org/I4210085935"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5054834255"],"corresponding_institution_ids":["https://openalex.org/I95457486"],"apc_list":null,"apc_paid":null,"fwci":39.1327,"has_fulltext":false,"cited_by_count":271,"citation_normalized_percentile":{"value":0.99752229,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"580","last_page":"591"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9994000196456909,"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":0.9994000196456909,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9979000091552734,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9965000152587891,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8196041584014893},{"id":"https://openalex.org/keywords/template","display_name":"Template","score":0.7814652919769287},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.6684018969535828},{"id":"https://openalex.org/keywords/hypertext","display_name":"Hypertext","score":0.5594576597213745},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.5565400719642639},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5331721901893616},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.44864708185195923},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.43920961022377014},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.1402117908000946},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1151907742023468}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8196041584014893},{"id":"https://openalex.org/C82714645","wikidata":"https://www.wikidata.org/wiki/Q438331","display_name":"Template","level":2,"score":0.7814652919769287},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.6684018969535828},{"id":"https://openalex.org/C162215914","wikidata":"https://www.wikidata.org/wiki/Q93241","display_name":"Hypertext","level":2,"score":0.5594576597213745},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.5565400719642639},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5331721901893616},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.44864708185195923},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.43920961022377014},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.1402117908000946},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1151907742023468},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/511446.511522","is_oa":false,"landing_page_url":"https://doi.org/10.1145/511446.511522","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 11th international conference on World Wide Web","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W336063547","https://openalex.org/W1489992655","https://openalex.org/W1506285740","https://openalex.org/W1538805611","https://openalex.org/W1549392931","https://openalex.org/W1854214752","https://openalex.org/W1970859146","https://openalex.org/W1987777228","https://openalex.org/W2005124845","https://openalex.org/W2005207065","https://openalex.org/W2006119904","https://openalex.org/W2011111873","https://openalex.org/W2015720094","https://openalex.org/W2037498077","https://openalex.org/W2053549370","https://openalex.org/W2066636486","https://openalex.org/W2076008912","https://openalex.org/W2079672501","https://openalex.org/W2089199911","https://openalex.org/W2100815879","https://openalex.org/W2126129257","https://openalex.org/W2138621811","https://openalex.org/W2151626491","https://openalex.org/W2152565070","https://openalex.org/W2156632103","https://openalex.org/W4240407914","https://openalex.org/W6637623960","https://openalex.org/W6639055396","https://openalex.org/W6683392976"],"related_works":["https://openalex.org/W1536970214","https://openalex.org/W1565135491","https://openalex.org/W1815780662","https://openalex.org/W2121300814","https://openalex.org/W2264492131","https://openalex.org/W2337877695","https://openalex.org/W4386443623","https://openalex.org/W2254657742","https://openalex.org/W2050926388","https://openalex.org/W330925889"],"abstract_inverted_index":{"We":[0,21,33],"formulate":[1],"and":[2,8,47,52,79],"propose":[3],"the":[4,24,31,39],"template":[5,77],"detection":[6,78],"problem,":[7],"suggest":[9],"a":[10,57,66],"practical":[11],"solution":[12],"for":[13],"it":[14],"based":[15],"on":[16,30],"counting":[17],"frequent":[18],"item":[19],"sets.":[20],"show":[22,53,81],"that":[23,54],"use":[25],"of":[26,60,62,71,89],"templates":[27,55],"is":[28],"pervasive":[29],"web.":[32],"describe":[34],"three":[35],"principles,":[36],"which":[37],"characterize":[38],"assumptions":[40],"made":[41],"by":[42],"hypertext":[43],"information":[44],"retrieval":[45],"(IR)":[46],"data":[48],"mining":[49],"(DM)":[50],"systems,":[51],"are":[56],"major":[58],"source":[59],"violation":[61],"these":[63],"principles.":[64],"As":[65],"consequence,":[67],"basic":[68],"\"pure\"":[69],"implementations":[70],"simple":[72],"search":[73],"algorithms":[74],"coupled":[75],"with":[76],"elimination":[80],"surprising":[82],"increases":[83],"in":[84],"precision":[85],"at":[86],"all":[87],"levels":[88],"recall.":[90]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":14},{"year":2015,"cited_by_count":20},{"year":2014,"cited_by_count":18},{"year":2013,"cited_by_count":18},{"year":2012,"cited_by_count":15}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
