{"id":"https://openalex.org/W2154116572","doi":"https://doi.org/10.1109/wi.2003.1241279","title":"A data-mining approach for optimizing performance of an incremental crawler","display_name":"A data-mining approach for optimizing performance of an incremental crawler","publication_year":2004,"publication_date":"2004-04-23","ids":{"openalex":"https://openalex.org/W2154116572","doi":"https://doi.org/10.1109/wi.2003.1241279","mag":"2154116572"},"language":"en","primary_location":{"id":"doi:10.1109/wi.2003.1241279","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wi.2003.1241279","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings IEEE/WIC International Conference on Web Intelligence (WI 2003)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5051861325","display_name":"H. Bullot","orcid":null},"institutions":[{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"H. Bullot","raw_affiliation_strings":["School of Computer & Communication Sciences, Swiss Federal Institute of Technology, Lausanne, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer & Communication Sciences, Swiss Federal Institute of Technology, Lausanne, Switzerland","institution_ids":["https://openalex.org/I5124864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018205016","display_name":"Shiva Gupta","orcid":null},"institutions":[{"id":"https://openalex.org/I68891433","display_name":"Indian Institute of Technology Delhi","ror":"https://ror.org/049tgcd06","country_code":"IN","type":"education","lineage":["https://openalex.org/I68891433"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"S.K. Gupta","raw_affiliation_strings":["Department of Computer Science, Indian Institute of Technology Delhi, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Indian Institute of Technology Delhi, India","institution_ids":["https://openalex.org/I68891433"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047987914","display_name":"Mukesh Mohania","orcid":"https://orcid.org/0000-0003-4429-1412"},"institutions":[{"id":"https://openalex.org/I4210103279","display_name":"IBM Research - India","ror":"https://ror.org/014wt7r80","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210103279","https://openalex.org/I4210114115"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"M.K. Mohania","raw_affiliation_strings":["IBM India Research Laboratory, Indian Institute of Technology, Hauz Khas, New Delhi, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM India Research Laboratory, Indian Institute of Technology, Hauz Khas, New Delhi, India","institution_ids":["https://openalex.org/I4210103279"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"610","last_page":"615"},"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":0.9657999873161316,"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":0.9455000162124634,"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/web-crawler","display_name":"Web crawler","score":0.9769484400749207},{"id":"https://openalex.org/keywords/focused-crawler","display_name":"Focused crawler","score":0.8491427898406982},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.769841194152832},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.5483539700508118},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5423865914344788},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.522347092628479},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.5210311412811279},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.4278731346130371},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4093628227710724},{"id":"https://openalex.org/keywords/static-web-page","display_name":"Static web page","score":0.18955492973327637},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.13840925693511963},{"id":"https://openalex.org/keywords/web-navigation","display_name":"Web navigation","score":0.11274939775466919}],"concepts":[{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.9769484400749207},{"id":"https://openalex.org/C73340581","wikidata":"https://www.wikidata.org/wiki/Q5463958","display_name":"Focused crawler","level":5,"score":0.8491427898406982},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.769841194152832},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.5483539700508118},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5423865914344788},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.522347092628479},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.5210311412811279},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.4278731346130371},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4093628227710724},{"id":"https://openalex.org/C173576120","wikidata":"https://www.wikidata.org/wiki/Q2641220","display_name":"Static web page","level":4,"score":0.18955492973327637},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.13840925693511963},{"id":"https://openalex.org/C61096286","wikidata":"https://www.wikidata.org/wiki/Q7978592","display_name":"Web navigation","level":3,"score":0.11274939775466919},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/wi.2003.1241279","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wi.2003.1241279","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings IEEE/WIC International Conference on Web Intelligence (WI 2003)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1566984846","https://openalex.org/W1613836731","https://openalex.org/W1674850363","https://openalex.org/W1987272746","https://openalex.org/W2007687650","https://openalex.org/W2016122268","https://openalex.org/W2029341294","https://openalex.org/W2029500199","https://openalex.org/W2030453570","https://openalex.org/W2059713800","https://openalex.org/W2099126271","https://openalex.org/W2162502927","https://openalex.org/W2295141584","https://openalex.org/W4251434705","https://openalex.org/W4285719527","https://openalex.org/W6634031162","https://openalex.org/W6647247683","https://openalex.org/W6654369015"],"related_works":["https://openalex.org/W1501777393","https://openalex.org/W2042034567","https://openalex.org/W2548443989","https://openalex.org/W2375180657","https://openalex.org/W4385695127","https://openalex.org/W2963706618","https://openalex.org/W2113184419","https://openalex.org/W2389761961","https://openalex.org/W1999548128","https://openalex.org/W4254300012"],"abstract_inverted_index":{"Crawlers":[0],"visit":[1],"the":[2,38,49,53,59],"Web":[3,10],"to":[4,13,19,55,63],"maintain":[5],"a":[6,41],"local":[7],"repository":[8],"of":[9,40],"pages":[11,61],"up":[12],"date.":[14],"We":[15],"introduce":[16],"another":[17],"perspective":[18],"build":[20],"an":[21],"effective":[22],"incremental":[23],"crawler.":[24],"Based":[25],"on":[26],"previous":[27],"work":[28],"in":[29],"this":[30],"field,":[31],"we":[32,35],"study":[33],"how":[34],"can":[36,51],"improve":[37],"performance":[39],"crawler":[42,54],"using":[43],"data-mining.":[44],"The":[45],"information":[46],"collected":[47],"from":[48],"users":[50],"help":[52],"know":[56],"which":[57],"are":[58],"popular":[60],"and":[62],"revisit":[64],"them":[65],"as":[66,68],"soon":[67],"possible.":[69]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2012,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
