{"id":"https://openalex.org/W2119426258","doi":"https://doi.org/10.1145/1242572.1242744","title":"First-order focused crawling","display_name":"First-order focused crawling","publication_year":2007,"publication_date":"2007-05-08","ids":{"openalex":"https://openalex.org/W2119426258","doi":"https://doi.org/10.1145/1242572.1242744","mag":"2119426258"},"language":"en","primary_location":{"id":"doi:10.1145/1242572.1242744","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1242572.1242744","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 16th 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/A5038384093","display_name":"Qingyang Xu","orcid":"https://orcid.org/0000-0003-3870-5551"},"institutions":[{"id":"https://openalex.org/I194450716","display_name":"Jilin University","ror":"https://ror.org/00js3aw79","country_code":"CN","type":"education","lineage":["https://openalex.org/I194450716"]},{"id":"https://openalex.org/I4210136497","display_name":"Jilin Medical University","ror":"https://ror.org/03mzw7781","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210136497"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Qingyang Xu","raw_affiliation_strings":["Jilin University","jilin University"],"affiliations":[{"raw_affiliation_string":"Jilin University","institution_ids":["https://openalex.org/I4210136497","https://openalex.org/I194450716"]},{"raw_affiliation_string":"jilin University","institution_ids":["https://openalex.org/I4210136497"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100636658","display_name":"Wanli Zuo","orcid":"https://orcid.org/0000-0002-9339-3426"},"institutions":[{"id":"https://openalex.org/I194450716","display_name":"Jilin University","ror":"https://ror.org/00js3aw79","country_code":"CN","type":"education","lineage":["https://openalex.org/I194450716"]},{"id":"https://openalex.org/I4210136497","display_name":"Jilin Medical University","ror":"https://ror.org/03mzw7781","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210136497"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wanli Zuo","raw_affiliation_strings":["Jilin University","jilin University"],"affiliations":[{"raw_affiliation_string":"Jilin University","institution_ids":["https://openalex.org/I4210136497","https://openalex.org/I194450716"]},{"raw_affiliation_string":"jilin University","institution_ids":["https://openalex.org/I4210136497"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5038384093"],"corresponding_institution_ids":["https://openalex.org/I194450716","https://openalex.org/I4210136497"],"apc_list":null,"apc_paid":null,"fwci":4.7475,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.95035244,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1159","last_page":"1160"},"is_retracted":false,"is_paratext":false,"is_xpac":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/T11644","display_name":"Spam and Phishing Detection","score":0.9916999936103821,"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9901999831199646,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/crawling","display_name":"Crawling","score":0.9335485696792603},{"id":"https://openalex.org/keywords/web-crawler","display_name":"Web crawler","score":0.8190467357635498},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7441911101341248},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.6470175385475159},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5997850298881531},{"id":"https://openalex.org/keywords/order","display_name":"Order (exchange)","score":0.5179964303970337},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4968443214893341},{"id":"https://openalex.org/keywords/focused-crawler","display_name":"Focused crawler","score":0.4898497760295868},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3813219368457794},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3281603455543518},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.2501102387905121},{"id":"https://openalex.org/keywords/static-web-page","display_name":"Static web page","score":0.09634533524513245},{"id":"https://openalex.org/keywords/web-navigation","display_name":"Web navigation","score":0.07124578952789307},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.060616254806518555}],"concepts":[{"id":"https://openalex.org/C100368936","wikidata":"https://www.wikidata.org/wiki/Q1411725","display_name":"Crawling","level":2,"score":0.9335485696792603},{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.8190467357635498},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7441911101341248},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.6470175385475159},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5997850298881531},{"id":"https://openalex.org/C182306322","wikidata":"https://www.wikidata.org/wiki/Q1779371","display_name":"Order (exchange)","level":2,"score":0.5179964303970337},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4968443214893341},{"id":"https://openalex.org/C73340581","wikidata":"https://www.wikidata.org/wiki/Q5463958","display_name":"Focused crawler","level":5,"score":0.4898497760295868},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3813219368457794},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3281603455543518},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.2501102387905121},{"id":"https://openalex.org/C173576120","wikidata":"https://www.wikidata.org/wiki/Q2641220","display_name":"Static web page","level":4,"score":0.09634533524513245},{"id":"https://openalex.org/C61096286","wikidata":"https://www.wikidata.org/wiki/Q7978592","display_name":"Web navigation","level":3,"score":0.07124578952789307},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.060616254806518555},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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":[{"id":"doi:10.1145/1242572.1242744","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1242572.1242744","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 16th international conference on World Wide Web","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5400000214576721,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"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/W2017726337","https://openalex.org/W2124673015","https://openalex.org/W2159532020","https://openalex.org/W6678701036"],"related_works":["https://openalex.org/W4385695127","https://openalex.org/W2375180657","https://openalex.org/W4248730791","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/W2372594123"],"abstract_inverted_index":{"This":[0],"paper":[1],"reports":[2],"a":[3],"new":[4],"general":[5],"framework":[6],"of":[7,25,65],"focused":[8,69],"web":[9],"crawling":[10,56],"based":[11],"on":[12],"\"relational":[13],"subgroup":[14,41],"discovery\".":[15],"Predicates":[16],"are":[17,38],"used":[18],"explicitly":[19],"to":[20],"represent":[21],"the":[22,30,55,61],"relevance":[23],"clues":[24],"those":[26],"unvisited":[27],"pages":[28],"in":[29],"crawl":[31],"frontier,":[32],"and":[33,51],"then":[34],"first-order":[35,68],"classification":[36],"rules":[37,47],"induced":[39],"using":[40],"discovery":[42],"technique.":[43],"The":[44],"learned":[45],"relational":[46],"with":[48,72],"sufficient":[49],"support":[50],"confidence":[52],"will":[53],"guide":[54],"process":[57],"afterwards.":[58],"We":[59],"present":[60],"many":[62],"interesting":[63],"features":[64],"our":[66],"proposed":[67],"crawler,":[70],"together":[71],"preliminary":[73],"promising":[74],"experimental":[75],"results.":[76]},"counts_by_year":[{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
