{"id":"https://openalex.org/W2034091417","doi":"https://doi.org/10.1109/dmo.2012.6329810","title":"Web crawler with URL signature — A performance study","display_name":"Web crawler with URL signature — A performance study","publication_year":2012,"publication_date":"2012-09-01","ids":{"openalex":"https://openalex.org/W2034091417","doi":"https://doi.org/10.1109/dmo.2012.6329810","mag":"2034091417"},"language":"en","primary_location":{"id":"doi:10.1109/dmo.2012.6329810","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dmo.2012.6329810","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 4th Conference on Data Mining and Optimization (DMO)","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/A5069570912","display_name":"Lay-Ki Soon","orcid":"https://orcid.org/0000-0002-8072-242X"},"institutions":[{"id":"https://openalex.org/I173029219","display_name":"Multimedia University","ror":"https://ror.org/04zrbnc33","country_code":"MY","type":"education","lineage":["https://openalex.org/I173029219"]}],"countries":["MY"],"is_corresponding":true,"raw_author_name":"Lay-Ki Soon","raw_affiliation_strings":["Faculty of Computing and Informatics, Multimedia University, Cyberjaya, Selangor Darul Ehsan, Malaysia","Faculty of Computing and Informatics, Multimedia University, Cyberjaya, Selangor, Malaysia"],"affiliations":[{"raw_affiliation_string":"Faculty of Computing and Informatics, Multimedia University, Cyberjaya, Selangor Darul Ehsan, Malaysia","institution_ids":["https://openalex.org/I173029219"]},{"raw_affiliation_string":"Faculty of Computing and Informatics, Multimedia University, Cyberjaya, Selangor, Malaysia","institution_ids":["https://openalex.org/I173029219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076268863","display_name":"Yee-Ern Ku","orcid":null},"institutions":[{"id":"https://openalex.org/I173029219","display_name":"Multimedia University","ror":"https://ror.org/04zrbnc33","country_code":"MY","type":"education","lineage":["https://openalex.org/I173029219"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"Yee-Ern Ku","raw_affiliation_strings":["Faculty of Computing and Informatics, Multimedia University, Cyberjaya, Selangor Darul Ehsan, Malaysia","Faculty of Computing and Informatics, Multimedia University, Cyberjaya, Selangor, Malaysia"],"affiliations":[{"raw_affiliation_string":"Faculty of Computing and Informatics, Multimedia University, Cyberjaya, Selangor Darul Ehsan, Malaysia","institution_ids":["https://openalex.org/I173029219"]},{"raw_affiliation_string":"Faculty of Computing and Informatics, Multimedia University, Cyberjaya, Selangor, Malaysia","institution_ids":["https://openalex.org/I173029219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100381299","display_name":"Sang Ho Lee","orcid":"https://orcid.org/0000-0002-4634-4904"},"institutions":[{"id":"https://openalex.org/I141371507","display_name":"Soongsil University","ror":"https://ror.org/017xnm587","country_code":"KR","type":"education","lineage":["https://openalex.org/I141371507"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sang Ho Lee","raw_affiliation_strings":["Department of Computer Science, Soongsil University, Seoul, South Korea","Department of Computer Science, Soongsil Univ., Seoul, Korea#TAB#"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Soongsil University, Seoul, South Korea","institution_ids":["https://openalex.org/I141371507"]},{"raw_affiliation_string":"Department of Computer Science, Soongsil Univ., Seoul, Korea#TAB#","institution_ids":["https://openalex.org/I141371507"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5069570912"],"corresponding_institution_ids":["https://openalex.org/I173029219"],"apc_list":null,"apc_paid":null,"fwci":1.4211,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.86992384,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"127","last_page":"130"},"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/T11478","display_name":"Caching and Content Delivery","score":0.9858999848365784,"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/T10742","display_name":"Peer-to-Peer Network Technologies","score":0.9804999828338623,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/web-crawler","display_name":"Web crawler","score":0.9220035672187805},{"id":"https://openalex.org/keywords/crawling","display_name":"Crawling","score":0.891815185546875},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7841616868972778},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.6232004165649414},{"id":"https://openalex.org/keywords/focused-crawler","display_name":"Focused crawler","score":0.6143325567245483},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.6100499629974365},{"id":"https://openalex.org/keywords/signature","display_name":"Signature (topology)","score":0.5998521447181702},{"id":"https://openalex.org/keywords/static-web-page","display_name":"Static web page","score":0.5468371510505676},{"id":"https://openalex.org/keywords/web-application","display_name":"Web application","score":0.4888736605644226},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.42884647846221924},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.32699108123779297},{"id":"https://openalex.org/keywords/web-development","display_name":"Web development","score":0.2701561450958252},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.05464187264442444}],"concepts":[{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.9220035672187805},{"id":"https://openalex.org/C100368936","wikidata":"https://www.wikidata.org/wiki/Q1411725","display_name":"Crawling","level":2,"score":0.891815185546875},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7841616868972778},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.6232004165649414},{"id":"https://openalex.org/C73340581","wikidata":"https://www.wikidata.org/wiki/Q5463958","display_name":"Focused crawler","level":5,"score":0.6143325567245483},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.6100499629974365},{"id":"https://openalex.org/C2779696439","wikidata":"https://www.wikidata.org/wiki/Q7512811","display_name":"Signature (topology)","level":2,"score":0.5998521447181702},{"id":"https://openalex.org/C173576120","wikidata":"https://www.wikidata.org/wiki/Q2641220","display_name":"Static web page","level":4,"score":0.5468371510505676},{"id":"https://openalex.org/C118643609","wikidata":"https://www.wikidata.org/wiki/Q189210","display_name":"Web application","level":2,"score":0.4888736605644226},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.42884647846221924},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.32699108123779297},{"id":"https://openalex.org/C79373723","wikidata":"https://www.wikidata.org/wiki/Q386275","display_name":"Web development","level":3,"score":0.2701561450958252},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.05464187264442444},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","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},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/dmo.2012.6329810","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dmo.2012.6329810","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 4th Conference on Data Mining and Optimization (DMO)","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":10,"referenced_works":["https://openalex.org/W39274486","https://openalex.org/W1503924817","https://openalex.org/W1518490746","https://openalex.org/W1597291463","https://openalex.org/W2046166587","https://openalex.org/W2105710024","https://openalex.org/W2545522789","https://openalex.org/W6601551412","https://openalex.org/W6631170498","https://openalex.org/W6635630797"],"related_works":["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/W2274831913","https://openalex.org/W2352686120","https://openalex.org/W4385695127","https://openalex.org/W2113184419"],"abstract_inverted_index":{"URL":[0,42,49,75],"signature":[1,50],"was":[2],"proposed":[3],"to":[4,11,53,71],"be":[5],"implemented":[6],"in":[7,37],"web":[8,15,19,33,59,64],"crawling,":[9],"aiming":[10],"avoid":[12],"processing":[13,56],"duplicated":[14,58],"pages":[16,60],"for":[17,62],"further":[18,63],"crawling.":[20],"In":[21],"this":[22],"paper,":[23],"we":[24,39],"present":[25],"our":[26],"performance":[27],"study":[28],"on":[29],"an":[30],"open":[31],"source":[32],"crawler":[34],"-":[35],"WebSPHINX,":[36],"which":[38],"have":[40],"embedded":[41],"signature.":[43,76],"The":[44],"experimental":[45],"result":[46],"indicates":[47],"that":[48],"is":[51],"able":[52],"reduce":[54],"the":[55,72],"of":[57],"significantly":[61],"crawling":[65],"at":[66],"a":[67],"negligible":[68],"cost":[69],"compared":[70],"one":[73],"without":[74]},"counts_by_year":[{"year":2017,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}