{"id":"https://openalex.org/W2099577094","doi":"https://doi.org/10.1109/icitst.2009.5402607","title":"Freshness of Web search engines: Improving performance of Web search engines using data mining techniques","display_name":"Freshness of Web search engines: Improving performance of Web search engines using data mining techniques","publication_year":2009,"publication_date":"2009-11-01","ids":{"openalex":"https://openalex.org/W2099577094","doi":"https://doi.org/10.1109/icitst.2009.5402607","mag":"2099577094"},"language":"en","primary_location":{"id":"doi:10.1109/icitst.2009.5402607","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icitst.2009.5402607","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 International Conference for Internet Technology and Secured Transactions, (ICITST)","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/A5005961887","display_name":"Sadegh Kharazmi","orcid":null},"institutions":[{"id":"https://openalex.org/I55547365","display_name":"Payame Noor University","ror":"https://ror.org/031699d98","country_code":"IR","type":"education","lineage":["https://openalex.org/I55547365"]},{"id":"https://openalex.org/I133529467","display_name":"Sharif University of Technology","ror":"https://ror.org/024c2fq17","country_code":"IR","type":"education","lineage":["https://openalex.org/I133529467"]}],"countries":["IR"],"is_corresponding":true,"raw_author_name":"S. Kharazmi","raw_affiliation_strings":["Faculty of Computer Engineering, Payame Noor University, Tehran, Iran","WI Laboratory, Department of Computer Engineering, Sharif University of Technology, Tehran, Iran"],"affiliations":[{"raw_affiliation_string":"Faculty of Computer Engineering, Payame Noor University, Tehran, Iran","institution_ids":["https://openalex.org/I55547365"]},{"raw_affiliation_string":"WI Laboratory, Department of Computer Engineering, Sharif University of Technology, Tehran, Iran","institution_ids":["https://openalex.org/I133529467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015698138","display_name":"Ali Farahmand Nejad","orcid":null},"institutions":[{"id":"https://openalex.org/I55547365","display_name":"Payame Noor University","ror":"https://ror.org/031699d98","country_code":"IR","type":"education","lineage":["https://openalex.org/I55547365"]},{"id":"https://openalex.org/I133529467","display_name":"Sharif University of Technology","ror":"https://ror.org/024c2fq17","country_code":"IR","type":"education","lineage":["https://openalex.org/I133529467"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"A.F. Nejad","raw_affiliation_strings":["Faculty of Computer Engineering, Payame Noor University, Tehran, Iran","WI Laboratory, Department of Computer Engineering, Sharif University of Technology, Tehran, Iran"],"affiliations":[{"raw_affiliation_string":"Faculty of Computer Engineering, Payame Noor University, Tehran, Iran","institution_ids":["https://openalex.org/I55547365"]},{"raw_affiliation_string":"WI Laboratory, Department of Computer Engineering, Sharif University of Technology, Tehran, Iran","institution_ids":["https://openalex.org/I133529467"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051258190","display_name":"Hassan Abolhassani","orcid":"https://orcid.org/0000-0002-4838-0407"},"institutions":[{"id":"https://openalex.org/I55547365","display_name":"Payame Noor University","ror":"https://ror.org/031699d98","country_code":"IR","type":"education","lineage":["https://openalex.org/I55547365"]},{"id":"https://openalex.org/I133529467","display_name":"Sharif University of Technology","ror":"https://ror.org/024c2fq17","country_code":"IR","type":"education","lineage":["https://openalex.org/I133529467"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"H. Abolhassani","raw_affiliation_strings":["Faculty of Computer Engineering, Payame Noor University, Tehran, Iran","WI Laboratory, Department of Computer Engineering, Sharif University of Technology, Tehran, Iran"],"affiliations":[{"raw_affiliation_string":"Faculty of Computer Engineering, Payame Noor University, Tehran, Iran","institution_ids":["https://openalex.org/I55547365"]},{"raw_affiliation_string":"WI Laboratory, Department of Computer Engineering, Sharif University of Technology, Tehran, Iran","institution_ids":["https://openalex.org/I133529467"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5005961887"],"corresponding_institution_ids":["https://openalex.org/I133529467","https://openalex.org/I55547365"],"apc_list":null,"apc_paid":null,"fwci":2.2209,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.91211062,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"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/T10260","display_name":"Software Engineering Research","score":0.9469000101089478,"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":0.9327999949455261,"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":0.9052492380142212},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7722172737121582},{"id":"https://openalex.org/keywords/crawling","display_name":"Crawling","score":0.7217981815338135},{"id":"https://openalex.org/keywords/focused-crawler","display_name":"Focused crawler","score":0.6954911351203918},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.6869533658027649},{"id":"https://openalex.org/keywords/web-search-engine","display_name":"Web search engine","score":0.6407926082611084},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.6324847936630249},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5289124250411987},{"id":"https://openalex.org/keywords/static-web-page","display_name":"Static web page","score":0.4421549439430237},{"id":"https://openalex.org/keywords/data-web","display_name":"Data Web","score":0.41409042477607727},{"id":"https://openalex.org/keywords/web-navigation","display_name":"Web navigation","score":0.31037747859954834}],"concepts":[{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.9052492380142212},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7722172737121582},{"id":"https://openalex.org/C100368936","wikidata":"https://www.wikidata.org/wiki/Q1411725","display_name":"Crawling","level":2,"score":0.7217981815338135},{"id":"https://openalex.org/C73340581","wikidata":"https://www.wikidata.org/wiki/Q5463958","display_name":"Focused crawler","level":5,"score":0.6954911351203918},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.6869533658027649},{"id":"https://openalex.org/C521815418","wikidata":"https://www.wikidata.org/wiki/Q4182287","display_name":"Web search engine","level":4,"score":0.6407926082611084},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.6324847936630249},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5289124250411987},{"id":"https://openalex.org/C173576120","wikidata":"https://www.wikidata.org/wiki/Q2641220","display_name":"Static web page","level":4,"score":0.4421549439430237},{"id":"https://openalex.org/C162005631","wikidata":"https://www.wikidata.org/wiki/Q54837","display_name":"Data Web","level":3,"score":0.41409042477607727},{"id":"https://openalex.org/C61096286","wikidata":"https://www.wikidata.org/wiki/Q7978592","display_name":"Web navigation","level":3,"score":0.31037747859954834},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","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:10.1109/icitst.2009.5402607","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icitst.2009.5402607","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 International Conference for Internet Technology and Secured Transactions, (ICITST)","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":22,"referenced_works":["https://openalex.org/W1489992655","https://openalex.org/W1503924817","https://openalex.org/W1504741607","https://openalex.org/W1566984846","https://openalex.org/W1987272746","https://openalex.org/W2003471189","https://openalex.org/W2008781077","https://openalex.org/W2029500199","https://openalex.org/W2038553416","https://openalex.org/W2046862025","https://openalex.org/W2066636486","https://openalex.org/W2094400120","https://openalex.org/W2108862625","https://openalex.org/W2121715962","https://openalex.org/W2141138294","https://openalex.org/W2143204586","https://openalex.org/W2147164982","https://openalex.org/W2159082584","https://openalex.org/W2162525956","https://openalex.org/W2165862792","https://openalex.org/W2169557227","https://openalex.org/W2170188121"],"related_works":["https://openalex.org/W2095543197","https://openalex.org/W2417265363","https://openalex.org/W2402678663","https://openalex.org/W2377634017","https://openalex.org/W3201526811","https://openalex.org/W2379145789","https://openalex.org/W2610451498","https://openalex.org/W1994958611","https://openalex.org/W4200125296","https://openalex.org/W2277785728"],"abstract_inverted_index":{"Progressive":[0],"use":[1],"of":[2,17,53,58,98],"Web":[3,19,26,39,47,59,70,126,197],"based":[4,27],"information":[5,28],"retrieval":[6,29],"systems":[7],"such":[8],"as":[9,136],"general":[10,195],"purpose":[11,142,196],"search":[12,60],"engines":[13],"and":[14,45,81,95,171],"dynamic":[15],"nature":[16],"the":[18,54,111],"make":[20],"it":[21,162],"necessary":[22],"to":[23,41,66,92,109,147,178],"continually":[24,82],"maintain":[25],"systems.":[30],"Crawlers":[31],"facilitate":[32],"this":[33,84,121,141],"process":[34,85],"by":[35,114,132,155,164],"following":[36],"hyperlinks":[37],"in":[38],"pages":[40],"automatically":[42],"download":[43],"new":[44],"updated":[46],"pages.":[48],"Freshness":[49],"(recency)":[50],"is":[51],"one":[52],"important":[55],"maintaining":[56],"factors":[57],"engine":[61],"crawlers":[62,71],"that":[63,89,102,128,185],"takes":[64],"weeks":[65],"months.":[67],"Many":[68],"large":[69],"start":[72],"from":[73,79,117],"seed":[74],"pages,":[75],"fetch":[76],"every":[77],"links":[78],"them,":[80],"repeat":[83],"without":[86],"any":[87],"policies":[88,137,174],"help":[90,107],"them":[91],"better":[93,191],"crawling":[94,118,150,169,177,186],"improving":[96],"performance":[97],"those.":[99],"We":[100],"believe":[101],"data":[103,133,170],"mining":[104,134,166],"techniques":[105,135,167],"can":[106],"us":[108],"improve":[110,179],"freshness":[112,180,192],"parameter":[113],"extracting":[115],"knowledge":[116,131],"data.":[119],"In":[120],"paper":[122],"we":[123,143],"propose":[124],"a":[125,145,159],"crawler":[127,153],"uses":[129,173],"extracted":[130],"for":[138,175],"crawling.":[139,157],"For":[140],"include":[144],"component":[146],"collect":[148],"additional":[149],"information.":[151],"This":[152],"starts":[154],"non-preferential":[156],"After":[158],"few":[160],"crawling,":[161],"trained":[163],"using":[165],"on":[168],"then":[172],"preferential":[176],"time.":[181],"Our":[182],"research":[183],"represented":[184],"with":[187],"determined":[188],"polices":[189],"has":[190],"than":[193],"generic":[194],"crawlers.":[198]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}