{"id":"https://openalex.org/W2394780948","doi":"https://doi.org/10.24348/sdnri.2014.coria-16","title":"Apprendre \u00e0 ordonner la fronti\u00e8re de crawl pour le crawling orient\u00e9.","display_name":"Apprendre \u00e0 ordonner la fronti\u00e8re de crawl pour le crawling orient\u00e9.","publication_year":2014,"publication_date":"2014-01-01","ids":{"openalex":"https://openalex.org/W2394780948","doi":"https://doi.org/10.24348/sdnri.2014.coria-16","mag":"2394780948"},"language":"fr","primary_location":{"id":"pmh:oai:HAL:hal-02492118v1","is_oa":false,"landing_page_url":"https://hal.science/hal-02492118","pdf_url":null,"source":{"id":"https://openalex.org/S4406922461","display_name":"SPIRE - Sciences Po Institutional REpository","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"COnf\u00e9rence en Recherche d'Information et ses Applications (CORIA 2014), 2014, Nancy, France. ⟨10.24348/sdnri.2014.coria-16⟩","raw_type":"Conference papers"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.24348/sdnri.2014.coria-16","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5048937960","display_name":"Cl\u00e9ment de Groc","orcid":null},"institutions":[{"id":"https://openalex.org/I102197404","display_name":"Universit\u00e9 Paris-Sud","ror":"https://ror.org/028rypz17","country_code":"FR","type":"education","lineage":["https://openalex.org/I102197404"]},{"id":"https://openalex.org/I4210115485","display_name":"Laboratoire d'Informatique pour la M\u00e9canique et les Sciences de l'Ing\u00e9nieur","ror":"https://ror.org/01raq4x89","country_code":"FR","type":"facility","lineage":["https://openalex.org/I102197404","https://openalex.org/I1294671590","https://openalex.org/I4210115485","https://openalex.org/I4210159245"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"De Groc, Cl\u00e9ment","raw_affiliation_strings":["Syllabs (15, rue Jean-Baptiste Berlier 75013 Paris - France)","LIMSI - Laboratoire d'Informatique pour la M\u00e9canique et les Sciences de l'Ing\u00e9nieur (Universit\u00e9 Paris-Sud B\u00e2t. 507 - Rue du Belv\u00e9d\u00e8re -91405 ORSAY CEDEX - France)"],"affiliations":[{"raw_affiliation_string":"Syllabs (15, rue Jean-Baptiste Berlier 75013 Paris - France)","institution_ids":[]},{"raw_affiliation_string":"LIMSI - Laboratoire d'Informatique pour la M\u00e9canique et les Sciences de l'Ing\u00e9nieur (Universit\u00e9 Paris-Sud B\u00e2t. 507 - Rue du Belv\u00e9d\u00e8re -91405 ORSAY CEDEX - France)","institution_ids":["https://openalex.org/I4210115485","https://openalex.org/I102197404"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056834851","display_name":"Xavier Tannier","orcid":"https://orcid.org/0000-0002-2452-8868"},"institutions":[{"id":"https://openalex.org/I102197404","display_name":"Universit\u00e9 Paris-Sud","ror":"https://ror.org/028rypz17","country_code":"FR","type":"education","lineage":["https://openalex.org/I102197404"]},{"id":"https://openalex.org/I4210115485","display_name":"Laboratoire d'Informatique pour la M\u00e9canique et les Sciences de l'Ing\u00e9nieur","ror":"https://ror.org/01raq4x89","country_code":"FR","type":"facility","lineage":["https://openalex.org/I102197404","https://openalex.org/I1294671590","https://openalex.org/I4210115485","https://openalex.org/I4210159245"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Tannier, Xavier","raw_affiliation_strings":["LIMSI - Laboratoire d'Informatique pour la M\u00e9canique et les Sciences de l'Ing\u00e9nieur (Universit\u00e9 Paris-Sud B\u00e2t. 507 - Rue du Belv\u00e9d\u00e8re -91405 ORSAY CEDEX - France)"],"affiliations":[{"raw_affiliation_string":"LIMSI - Laboratoire d'Informatique pour la M\u00e9canique et les Sciences de l'Ing\u00e9nieur (Universit\u00e9 Paris-Sud B\u00e2t. 507 - Rue du Belv\u00e9d\u00e8re -91405 ORSAY CEDEX - France)","institution_ids":["https://openalex.org/I4210115485","https://openalex.org/I102197404"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5048937960"],"corresponding_institution_ids":["https://openalex.org/I102197404","https://openalex.org/I4210115485"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.40675609,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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/T10260","display_name":"Software Engineering Research","score":0.9869999885559082,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9609000086784363,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/humanities","display_name":"Humanities","score":0.7179980874061584},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.42573556303977966},{"id":"https://openalex.org/keywords/political-science","display_name":"Political science","score":0.41522231698036194},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.24347269535064697}],"concepts":[{"id":"https://openalex.org/C15708023","wikidata":"https://www.wikidata.org/wiki/Q80083","display_name":"Humanities","level":1,"score":0.7179980874061584},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.42573556303977966},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.41522231698036194},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.24347269535064697}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:HAL:hal-02492118v1","is_oa":false,"landing_page_url":"https://hal.science/hal-02492118","pdf_url":null,"source":{"id":"https://openalex.org/S4406922461","display_name":"SPIRE - Sciences Po Institutional REpository","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"COnf\u00e9rence en Recherche d'Information et ses Applications (CORIA 2014), 2014, Nancy, France. ⟨10.24348/sdnri.2014.coria-16⟩","raw_type":"Conference papers"},{"id":"doi:10.24348/sdnri.2014.coria-16","is_oa":true,"landing_page_url":"https://doi.org/10.24348/sdnri.2014.coria-16","pdf_url":null,"source":{"id":"https://openalex.org/S7407051734","display_name":"Association en Recherche d\u2019Information et Applications","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"doi:10.24348/sdnri.2014.coria-16","is_oa":true,"landing_page_url":"https://doi.org/10.24348/sdnri.2014.coria-16","pdf_url":null,"source":{"id":"https://openalex.org/S7407051734","display_name":"Association en Recherche d\u2019Information et Applications","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article-journal"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W116870935","https://openalex.org/W1481372933","https://openalex.org/W1489992655","https://openalex.org/W1532325895","https://openalex.org/W1543096214","https://openalex.org/W1678356000","https://openalex.org/W1973435495","https://openalex.org/W1980318031","https://openalex.org/W1990589796","https://openalex.org/W2001832505","https://openalex.org/W2007815473","https://openalex.org/W2014134732","https://openalex.org/W2017726337","https://openalex.org/W2023607075","https://openalex.org/W2029341294","https://openalex.org/W2044743392","https://openalex.org/W2093347820","https://openalex.org/W2102942431","https://openalex.org/W2118585731","https://openalex.org/W2121017700","https://openalex.org/W2124673015","https://openalex.org/W2142211218","https://openalex.org/W2143806604","https://openalex.org/W2151007976","https://openalex.org/W2152805927","https://openalex.org/W2162059449","https://openalex.org/W2163455955","https://openalex.org/W2170611687","https://openalex.org/W2884475480","https://openalex.org/W2899025540","https://openalex.org/W2911388033","https://openalex.org/W2988119488"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W93312527","https://openalex.org/W2382290278","https://openalex.org/W4391913857","https://openalex.org/W2350741829"],"abstract_inverted_index":{"R\u00c9SUM\u00c9.":[0],"Le":[1],"crawling":[2],"orient\u00e9":[3],"consiste":[4],"\u00e0":[5,43,118],"parcourir":[6],"le":[7],"Web":[8],"au":[9],"travers":[10],"des":[11,19],"hyperliens":[12],"en":[13,17],"orientant":[14],"son":[15],"parcours":[16],"direction":[18],"pages":[20],"pertinentes.":[21],"Pour":[22],"cela,":[23],"ces":[24],"crawlers":[25],"ordonnent":[26],"leurs":[27],"t\u00e9l\u00e9chargements":[28],"suivant":[29],"une":[30,67,71],"strat\u00e9gie":[31],"d'ordonnancement.":[32],"Dans":[33],"cet":[34],"article,":[35],"nous":[36,51,124],"proposons":[37],"d'ap-":[38],"prendre":[39],"cette":[40],"fonction":[41,72],"d'ordonnancement":[42,73],"partir":[44],"de":[45,58,62,82,89,92,101,112,114,130,137],"donn\u00e9es":[46],"annot\u00e9es.":[47],"Une":[48],"telle":[49],"approche":[50,87],"permet":[52,108],"notamment":[53],"d'int\u00e9grer":[54],"un":[55],"grand":[56],"nombre":[57],"traits":[59],"h\u00e9t\u00e9rog\u00e8nes":[60],"et":[61,103,128],"les":[63,126,135],"combiner.":[64],"Nous":[65,84],"d\u00e9crivons":[66],"m\u00e9thode":[68,107],"permettant":[69],"d'apprendre":[70],"ind\u00e9pen-":[74],"dante":[75],"du":[76],"domaine":[77],"pour":[78],"la":[79,110],"collecte":[80],"th\u00e9matique":[81],"documents.":[83],"\u00e9valuons":[85],"notre":[86,106,131],"sur":[88,96],"\"longs\"":[90],"crawls":[91],"40":[93],"000":[94],"documents":[95],"15":[97],"th\u00e8mes":[98],"diff\u00e9rents":[99],"issus":[100],"l'OpenDirectory,":[102],"montrons":[104],"que":[105,134],"d'am\u00e9liorer":[109],"pr\u00e9cision":[111],"pr\u00e8s":[113],"10%":[115],"par":[116],"rapport":[117],"l'al-":[119],"gorithme":[120],"Shark":[121],"Search.":[122],"Enfin,":[123],"discutons":[125],"avantages":[127],"inconv\u00e9nients":[129],"approche,":[132],"ainsi":[133],"pistes":[136],"recherche":[138],"ouvertes.":[139]},"counts_by_year":[],"updated_date":"2026-03-22T08:09:32.410652","created_date":"2016-06-24T00:00:00"}