{"id":"https://openalex.org/W1995663744","doi":"https://doi.org/10.1145/1998076.1998098","title":"Archiving the web using page changes patterns","display_name":"Archiving the web using page changes patterns","publication_year":2011,"publication_date":"2011-06-13","ids":{"openalex":"https://openalex.org/W1995663744","doi":"https://doi.org/10.1145/1998076.1998098","mag":"1995663744"},"language":"en","primary_location":{"id":"doi:10.1145/1998076.1998098","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1998076.1998098","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 11th annual international ACM/IEEE joint conference on Digital libraries","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/A5002391290","display_name":"Myriam Ben Sa\u00e2d","orcid":"https://orcid.org/0009-0008-2131-9922"},"institutions":[{"id":"https://openalex.org/I4210159731","display_name":"LIP6","ror":"https://ror.org/05krcen59","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I39804081","https://openalex.org/I4210159245","https://openalex.org/I4210159731"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Myriam Ben Saad","raw_affiliation_strings":["LIP6, University P. and M. Curie, Paris, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LIP6, University P. and M. Curie, Paris, France","institution_ids":["https://openalex.org/I4210159731"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049035512","display_name":"St\u00e9phane Gan\u00e7arski","orcid":"https://orcid.org/0000-0002-5252-5314"},"institutions":[{"id":"https://openalex.org/I4210159731","display_name":"LIP6","ror":"https://ror.org/05krcen59","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I39804081","https://openalex.org/I4210159245","https://openalex.org/I4210159731"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"St\u00e9phane Gan\u00e7arski","raw_affiliation_strings":["LIP6, University P. and M. Curie, Paris, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LIP6, University P. and M. Curie, Paris, France","institution_ids":["https://openalex.org/I4210159731"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210159731"],"apc_list":null,"apc_paid":null,"fwci":9.8655,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.97628768,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"113","last_page":"122"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9994999766349792,"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":0.9994999766349792,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.996399998664856,"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/T10742","display_name":"Peer-to-Peer Network Technologies","score":0.987500011920929,"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/computer-science","display_name":"Computer science","score":0.8150612115859985},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5648836493492126},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.5398008823394775},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.5126535296440125},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.5044306516647339},{"id":"https://openalex.org/keywords/web-mining","display_name":"Web mining","score":0.45899397134780884},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4580993950366974},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4411192536354065},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.4384571313858032},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.43238240480422974},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4037604033946991},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.39737990498542786}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8150612115859985},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5648836493492126},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.5398008823394775},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.5126535296440125},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.5044306516647339},{"id":"https://openalex.org/C197046077","wikidata":"https://www.wikidata.org/wiki/Q785337","display_name":"Web mining","level":3,"score":0.45899397134780884},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4580993950366974},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4411192536354065},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.4384571313858032},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.43238240480422974},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4037604033946991},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.39737990498542786},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1998076.1998098","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1998076.1998098","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 11th annual international ACM/IEEE joint conference on Digital libraries","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":47,"referenced_works":["https://openalex.org/W14978841","https://openalex.org/W608337257","https://openalex.org/W1522137439","https://openalex.org/W1536535841","https://openalex.org/W1556347322","https://openalex.org/W1566984846","https://openalex.org/W1567790484","https://openalex.org/W1595130292","https://openalex.org/W1661413208","https://openalex.org/W1669209061","https://openalex.org/W1803802947","https://openalex.org/W1814217792","https://openalex.org/W1976624301","https://openalex.org/W1995821742","https://openalex.org/W2018928332","https://openalex.org/W2021314079","https://openalex.org/W2029341294","https://openalex.org/W2030453570","https://openalex.org/W2038378248","https://openalex.org/W2042261949","https://openalex.org/W2055613486","https://openalex.org/W2059713800","https://openalex.org/W2063771604","https://openalex.org/W2093532875","https://openalex.org/W2099126271","https://openalex.org/W2105730821","https://openalex.org/W2110073539","https://openalex.org/W2110893883","https://openalex.org/W2113889316","https://openalex.org/W2117169652","https://openalex.org/W2127536142","https://openalex.org/W2135402295","https://openalex.org/W2138310207","https://openalex.org/W2148931201","https://openalex.org/W2151932833","https://openalex.org/W2152801867","https://openalex.org/W2153083299","https://openalex.org/W2163941332","https://openalex.org/W2164851407","https://openalex.org/W2167859982","https://openalex.org/W2171070229","https://openalex.org/W2741909411","https://openalex.org/W2913520302","https://openalex.org/W3095267943","https://openalex.org/W3204318296","https://openalex.org/W4285719527","https://openalex.org/W6758471461"],"related_works":["https://openalex.org/W17155033","https://openalex.org/W3207760230","https://openalex.org/W1496222301","https://openalex.org/W4312814274","https://openalex.org/W1590307681","https://openalex.org/W2536018345","https://openalex.org/W4285370786","https://openalex.org/W2296488620","https://openalex.org/W2083329789","https://openalex.org/W2376574812"],"abstract_inverted_index":{"A":[0],"pattern":[1,45,161],"is":[2,121],"a":[3,6,19,29,211],"model":[4,162],"or":[5,64,89,96,241],"template":[7],"used":[8,52,112,174],"to":[9,80,83,92,97,102,152,175,184,189,193,216,233,238],"summarize":[10],"and":[11,35,51,127,188,237],"describe":[12],"the":[13,16,40,103,114,122,131,165,172,178,199,229],"behavior":[14,86],"(or":[15,87],"trend)":[17],"of":[18,105,116,124,130,145,167,181,201,231],"data":[20,41,66,69,85,94],"having":[21],"generally":[22],"some":[23],"recurrent":[24],"events.":[25],"Patterns":[26],"have":[27,48,109],"received":[28],"considerable":[30],"attention":[31],"in":[32,39,113,214],"recent":[33],"years":[34],"were":[36,78],"widely":[37],"studied":[38],"mining":[42,46],"field.":[43],"Various":[44],"approaches":[47],"been":[49,111],"proposed":[50],"for":[53,135],"different":[54,74],"applications":[55],"such":[56],"as":[57,210],"network":[58],"monitoring,":[59],"moving":[60],"object":[61],"tracking,":[62],"financial":[63],"medical":[65],"analysis,":[67],"scientific":[68],"processing,":[70],"etc.":[71],"In":[72,138],"these":[73],"contexts,":[75],"discovered":[76],"patterns":[77,108,144,187,232],"useful":[79,150],"detect":[81],"anomalies,":[82],"predict":[84],"trend),":[88],"more":[90],"generally,":[91],"simplify":[93],"processing":[95],"improve":[98,194,234],"system":[99],"performance.":[100],"However,":[101],"best":[104],"our":[106,160,218],"knowledge,":[107],"never":[110],"context":[115],"web":[117,155,195,226],"archiving.":[118],"Web":[119,134],"archiving":[120],"process":[123],"continuously":[125],"collecting":[126],"preserving":[128],"portions":[129],"World":[132],"Wide":[133],"future":[136],"generations.":[137],"this":[139],"paper,":[140],"we":[141,170],"show":[142],"how":[143],"page":[146,182],"changes":[147,166],"can":[148],"be":[149],"tools":[151],"efficiently":[153],"archive":[154,200,235],"sites.":[156],"We":[157,197],"first":[158],"define":[159],"that":[163],"describes":[164],"pages.":[168],"Then,":[169],"present":[171],"strategy":[173],"(i)":[176],"extract":[177],"temporal":[179],"evolution":[180],"changes,":[183],"(ii)":[185],"discover":[186],"(iii)":[190],"exploit":[191],"them":[192],"archives.":[196],"choose":[198],"French":[202],"public":[203],"TV":[204],"channels":[205],"\u00ab":[206],"France":[207],"T\u00e9l\u00e9visions":[208],"\u00bb":[209],"case":[212],"study":[213],"order":[215],"validate":[217],"approach.":[219],"Our":[220],"experimental":[221],"evaluation":[222],"based":[223],"on":[224],"real":[225],"pages":[227],"shows":[228],"utility":[230],"quality":[236],"optimize":[239],"indexing":[240],"storing.":[242]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":6},{"year":2012,"cited_by_count":2}],"updated_date":"2026-03-25T13:04:00.132906","created_date":"2025-10-10T00:00:00"}
