{"id":"https://openalex.org/W2171686321","doi":"https://doi.org/10.1145/1062745.1062933","title":"Focused crawling by exploiting anchor text using decision tree","display_name":"Focused crawling by exploiting anchor text using decision tree","publication_year":2005,"publication_date":"2005-01-01","ids":{"openalex":"https://openalex.org/W2171686321","doi":"https://doi.org/10.1145/1062745.1062933","mag":"2171686321"},"language":"en","primary_location":{"id":"doi:10.1145/1062745.1062933","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1062745.1062933","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Special interest tracks and posters of the 14th international conference on World Wide Web - WWW '05","raw_type":"proceedings-article"},"type":"conference-abstract","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/A5100697979","display_name":"Jun Li","orcid":"https://orcid.org/0000-0003-3716-671X"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Jun Li","raw_affiliation_strings":["The University of Tokyo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Tokyo","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057449091","display_name":"Kazutaka Furuse","orcid":"https://orcid.org/0009-0001-7473-8783"},"institutions":[{"id":"https://openalex.org/I146399215","display_name":"University of Tsukuba","ror":"https://ror.org/02956yf07","country_code":"JP","type":"education","lineage":["https://openalex.org/I146399215"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kazutaka Furuse","raw_affiliation_strings":["University of Tsukuba"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tsukuba","institution_ids":["https://openalex.org/I146399215"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029259830","display_name":"Kazunori Yamaguchi","orcid":"https://orcid.org/0000-0003-0383-7386"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kazunori Yamaguchi","raw_affiliation_strings":["The University of Tokyo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Tokyo","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":35,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1190","last_page":"1190"},"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/T11106","display_name":"Data Management and Algorithms","score":0.9708999991416931,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T13976","display_name":"Web visibility and informetrics","score":0.9557999968528748,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/crawling","display_name":"Crawling","score":0.8250175714492798},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8189737796783447},{"id":"https://openalex.org/keywords/web-crawler","display_name":"Web crawler","score":0.791945219039917},{"id":"https://openalex.org/keywords/hyperlink","display_name":"Hyperlink","score":0.7746517658233643},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7200254201889038},{"id":"https://openalex.org/keywords/focused-crawler","display_name":"Focused crawler","score":0.5872144103050232},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.5836446285247803},{"id":"https://openalex.org/keywords/decision-tree","display_name":"Decision tree","score":0.5811605453491211},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5526500344276428},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4806765019893646},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.4088664650917053},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.222962886095047},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.1914752721786499},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.16261577606201172},{"id":"https://openalex.org/keywords/web-server","display_name":"Web server","score":0.12660905718803406}],"concepts":[{"id":"https://openalex.org/C100368936","wikidata":"https://www.wikidata.org/wiki/Q1411725","display_name":"Crawling","level":2,"score":0.8250175714492798},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8189737796783447},{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.791945219039917},{"id":"https://openalex.org/C30088001","wikidata":"https://www.wikidata.org/wiki/Q102014","display_name":"Hyperlink","level":3,"score":0.7746517658233643},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7200254201889038},{"id":"https://openalex.org/C73340581","wikidata":"https://www.wikidata.org/wiki/Q5463958","display_name":"Focused crawler","level":5,"score":0.5872144103050232},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.5836446285247803},{"id":"https://openalex.org/C84525736","wikidata":"https://www.wikidata.org/wiki/Q831366","display_name":"Decision tree","level":2,"score":0.5811605453491211},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5526500344276428},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4806765019893646},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.4088664650917053},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.222962886095047},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.1914752721786499},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.16261577606201172},{"id":"https://openalex.org/C11392498","wikidata":"https://www.wikidata.org/wiki/Q11288","display_name":"Web server","level":3,"score":0.12660905718803406},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C105702510","wikidata":"https://www.wikidata.org/wiki/Q514","display_name":"Anatomy","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C173576120","wikidata":"https://www.wikidata.org/wiki/Q2641220","display_name":"Static web page","level":4,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1062745.1062933","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1062745.1062933","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Special interest tracks and posters of the 14th international conference on World Wide Web - WWW '05","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.6200000047683716,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W1489992655","https://openalex.org/W2124673015","https://openalex.org/W2149706766","https://openalex.org/W3121299688","https://openalex.org/W3139831614"],"related_works":["https://openalex.org/W4385695127","https://openalex.org/W2375180657","https://openalex.org/W2042034567","https://openalex.org/W2026132847","https://openalex.org/W1506122440","https://openalex.org/W2137810919","https://openalex.org/W2358310581","https://openalex.org/W2352686120","https://openalex.org/W2019080882","https://openalex.org/W2274831913"],"abstract_inverted_index":{"Focused":[0],"crawlers":[1],"are":[2],"considered":[3],"as":[4],"a":[5,21,39,42],"promising":[6],"way":[7],"to":[8],"tackle":[9],"the":[10,24,54],"scalability":[11],"problem":[12],"of":[13,26,48,58],"topic-oriented":[14],"or":[15],"personalized":[16],"search":[17],"engines.":[18],"To":[19],"design":[20],"focused":[22],"crawler,":[23],"choice":[25],"strategy":[27],"for":[28],"prioritizing":[29],"unvisited":[30],"URLs":[31],"is":[32],"crucial.":[33],"In":[34],"this":[35],"paper,":[36],"we":[37],"propose":[38],"method":[40],"using":[41],"decision":[43],"tree":[44],"on":[45,53],"anchor":[46],"texts":[47],"hyperlinks.":[49],"We":[50],"conducted":[51],"experiments":[52],"real":[55],"data":[56],"sets":[57],"four":[59],"Japanese":[60],"universities":[61],"and":[62],"verified":[63],"our":[64],"approach.":[65]},"counts_by_year":[{"year":2022,"cited_by_count":3},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-19T07:52:34.831488","created_date":"2025-10-10T00:00:00"}
