{"id":"https://openalex.org/W1999217709","doi":"https://doi.org/10.1109/la-web.2012.24","title":"Improving the Efficiency of a Genre-Aware Approach to Focused Crawling Based on Link Context","display_name":"Improving the Efficiency of a Genre-Aware Approach to Focused Crawling Based on Link Context","publication_year":2012,"publication_date":"2012-10-01","ids":{"openalex":"https://openalex.org/W1999217709","doi":"https://doi.org/10.1109/la-web.2012.24","mag":"1999217709"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/la-web.2012.24","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"proceedings-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/A5024201468","display_name":"V\u00edtor Mangaravite","orcid":"https://orcid.org/0000-0001-9824-5484"},"institutions":[{"id":"https://openalex.org/I10824318","display_name":"Universidade Federal de Ouro Preto","ror":"https://ror.org/056s65p46","country_code":"BR","type":"education","lineage":["https://openalex.org/I10824318"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Vitor Mangaravite","raw_affiliation_strings":["Comput. Sci. Dept., Fed. Univ. of Ouro Preto, Ouro Preto, Brazil"],"affiliations":[{"raw_affiliation_string":"Comput. Sci. Dept., Fed. Univ. of Ouro Preto, Ouro Preto, Brazil","institution_ids":["https://openalex.org/I10824318"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044273290","display_name":"Guilherme T. de Assis","orcid":null},"institutions":[{"id":"https://openalex.org/I10824318","display_name":"Universidade Federal de Ouro Preto","ror":"https://ror.org/056s65p46","country_code":"BR","type":"education","lineage":["https://openalex.org/I10824318"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Guilherme Tavares_de_ Assis","raw_affiliation_strings":["Comput. Sci. Dept., Fed. Univ. of Ouro Preto, Ouro Preto, Brazil"],"affiliations":[{"raw_affiliation_string":"Comput. Sci. Dept., Fed. Univ. of Ouro Preto, Ouro Preto, Brazil","institution_ids":["https://openalex.org/I10824318"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011076740","display_name":"Anderson A. Ferreira","orcid":"https://orcid.org/0000-0002-2487-6600"},"institutions":[{"id":"https://openalex.org/I10824318","display_name":"Universidade Federal de Ouro Preto","ror":"https://ror.org/056s65p46","country_code":"BR","type":"education","lineage":["https://openalex.org/I10824318"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Anderson A. Ferreira","raw_affiliation_strings":["Comput. Sci. Dept., Fed. Univ. of Ouro Preto, Ouro Preto, Brazil"],"affiliations":[{"raw_affiliation_string":"Comput. Sci. Dept., Fed. Univ. of Ouro Preto, Ouro Preto, Brazil","institution_ids":["https://openalex.org/I10824318"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.577,"has_fulltext":true,"fulltext_origin":"ngrams","cited_by_count":9,"citation_normalized_percentile":{"value":0.711796,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":84,"max":85},"biblio":{"volume":null,"issue":null,"first_page":"17","last_page":"23"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":1.0,"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":1.0,"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/T11478","display_name":"Caching and Content Delivery","score":0.983,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T11644","display_name":"Spam and Phishing Detection","score":0.9752,"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":0.9073639},{"id":"https://openalex.org/keywords/web-crawler","display_name":"Web crawler","score":0.83399546},{"id":"https://openalex.org/keywords/focused-crawler","display_name":"Focused crawler","score":0.6642364}],"concepts":[{"id":"https://openalex.org/C100368936","wikidata":"https://www.wikidata.org/wiki/Q1411725","display_name":"Crawling","level":2,"score":0.9073639},{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.83399546},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7848662},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.66599905},{"id":"https://openalex.org/C73340581","wikidata":"https://www.wikidata.org/wiki/Q5463958","display_name":"Focused crawler","level":5,"score":0.6642364},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.653628},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.43436056},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.42100638},{"id":"https://openalex.org/C61096286","wikidata":"https://www.wikidata.org/wiki/Q7978592","display_name":"Web navigation","level":3,"score":0.20759663},{"id":"https://openalex.org/C173576120","wikidata":"https://www.wikidata.org/wiki/Q2641220","display_name":"Static web page","level":4,"score":0.15701032},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C105702510","wikidata":"https://www.wikidata.org/wiki/Q514","display_name":"Anatomy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/la-web.2012.24","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false}],"best_oa_location":null,"sustainable_development_goals":[],"grants":[],"datasets":[],"versions":[],"referenced_works_count":24,"referenced_works":["https://openalex.org/W1489992655","https://openalex.org/W1503924817","https://openalex.org/W1566984846","https://openalex.org/W1573640501","https://openalex.org/W160262995","https://openalex.org/W1660390307","https://openalex.org/W1674850363","https://openalex.org/W1965773314","https://openalex.org/W1999267468","https://openalex.org/W2005579877","https://openalex.org/W2017224880","https://openalex.org/W2029341294","https://openalex.org/W2045998703","https://openalex.org/W2078076527","https://openalex.org/W2081128931","https://openalex.org/W2102942431","https://openalex.org/W2151007976","https://openalex.org/W2156963321","https://openalex.org/W2162630660","https://openalex.org/W2169917945","https://openalex.org/W2171686321","https://openalex.org/W2330384907","https://openalex.org/W4235996464","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W4385695127","https://openalex.org/W4248730791","https://openalex.org/W2375180657","https://openalex.org/W2372594123","https://openalex.org/W2358310581","https://openalex.org/W2352686120","https://openalex.org/W2137810919","https://openalex.org/W2026132847","https://openalex.org/W2019080882","https://openalex.org/W1506122440"],"abstract_inverted_index":{"Focused":[0,34],"crawlers":[1,21,35],"attempt":[2],"to":[3,10,25,30,43,69],"crawl":[4],"web":[5,46],"pages":[6,47],"that":[7],"are":[8],"relevant":[9],"a":[11,38,59,74],"specific":[12],"topic":[13],"or":[14],"user":[15],"interest.":[16],"Although":[17],"these":[18],"kinds":[19],"of":[20,40,62,73],"have":[22],"been":[23],"proven":[24],"be":[26],"effective,":[27],"they":[28],"need":[29],"improve":[31,70],"their":[32],"efficiency.":[33],"usually":[36],"use":[37],"Frontier":[39],"non-visited":[41,63],"URLs":[42],"visit":[44],"the":[45,71],"and":[48,57],"gather":[49],"relavant":[50],"ones.":[51],"In":[52],"this":[53],"work,":[54],"we":[55],"define":[56],"evaluate":[58],"queueing":[60],"policy":[61],"URLs,":[64],"based":[65],"on":[66],"link":[67],"context,":[68],"efficiency":[72,90],"genre-aware":[75],"focused":[76],"crawler.":[77],"Our":[78],"experimental":[79],"evaluation":[80],"shows,":[81],"in":[82,89],"some":[83],"situations,":[84],"an":[85],"improvement":[86],"around":[87],"100%":[88],"terms.":[91]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W1999217709","counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":2}],"updated_date":"2024-12-16T20:27:15.065104","created_date":"2016-06-24"}