{"id":"https://openalex.org/W2006910506","doi":"https://doi.org/10.1109/rcis.2010.5507394","title":"Combining agents and Wrapper Induction for information gathering on restricted web domains","display_name":"Combining agents and Wrapper Induction for information gathering on restricted web domains","publication_year":2010,"publication_date":"2010-05-01","ids":{"openalex":"https://openalex.org/W2006910506","doi":"https://doi.org/10.1109/rcis.2010.5507394","mag":"2006910506"},"language":"en","primary_location":{"id":"doi:10.1109/rcis.2010.5507394","is_oa":false,"landing_page_url":"https://doi.org/10.1109/rcis.2010.5507394","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 Fourth International Conference on Research Challenges in Information Science (RCIS)","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/A5025426575","display_name":"Shereen Albitar","orcid":null},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210125985","display_name":"Institut Fresnel","ror":"https://ror.org/03br1wy20","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I21491767","https://openalex.org/I4210095849","https://openalex.org/I4210125985","https://openalex.org/I4210142724"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Shereen Albitar","raw_affiliation_strings":["LSIS UMR CNRS 6168, Domaine Universitaire de St Jer\u00f4me, Marseille Cedex 20, France","LSIS UMR CNRS 6168, Universit\u00e9 d'Aix-Marseille, Domaine Universitaire de St Jer\u00f4me, F-13997, Marseille Cedex 20, France"],"affiliations":[{"raw_affiliation_string":"LSIS UMR CNRS 6168, Domaine Universitaire de St Jer\u00f4me, Marseille Cedex 20, France","institution_ids":["https://openalex.org/I4210125985","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"LSIS UMR CNRS 6168, Universit\u00e9 d'Aix-Marseille, Domaine Universitaire de St Jer\u00f4me, F-13997, Marseille Cedex 20, France","institution_ids":["https://openalex.org/I1294671590"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109066626","display_name":"Bernard Espinasse","orcid":null},"institutions":[{"id":"https://openalex.org/I4210125985","display_name":"Institut Fresnel","ror":"https://ror.org/03br1wy20","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I21491767","https://openalex.org/I4210095849","https://openalex.org/I4210125985","https://openalex.org/I4210142724"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1294671590"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Bernard Espinasse","raw_affiliation_strings":["LSIS UMR CNRS 6168, Domaine Universitaire de St Jer\u00f4me, Marseille Cedex 20, France","LSIS UMR CNRS 6168, Universit\u00e9 d'Aix-Marseille, Domaine Universitaire de St Jer\u00f4me, F-13997, Marseille Cedex 20, France"],"affiliations":[{"raw_affiliation_string":"LSIS UMR CNRS 6168, Domaine Universitaire de St Jer\u00f4me, Marseille Cedex 20, France","institution_ids":["https://openalex.org/I4210125985","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"LSIS UMR CNRS 6168, Universit\u00e9 d'Aix-Marseille, Domaine Universitaire de St Jer\u00f4me, F-13997, Marseille Cedex 20, France","institution_ids":["https://openalex.org/I1294671590"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058109847","display_name":"S\u00e9bastien Fournier","orcid":"https://orcid.org/0000-0002-1611-0744"},"institutions":[{"id":"https://openalex.org/I4210125985","display_name":"Institut Fresnel","ror":"https://ror.org/03br1wy20","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I21491767","https://openalex.org/I4210095849","https://openalex.org/I4210125985","https://openalex.org/I4210142724"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1294671590"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Sebastien Fournier","raw_affiliation_strings":["LSIS UMR CNRS 6168, Domaine Universitaire de St Jer\u00f4me, Marseille Cedex 20, France","LSIS UMR CNRS 6168, Universit\u00e9 d'Aix-Marseille, Domaine Universitaire de St Jer\u00f4me, F-13997, Marseille Cedex 20, France"],"affiliations":[{"raw_affiliation_string":"LSIS UMR CNRS 6168, Domaine Universitaire de St Jer\u00f4me, Marseille Cedex 20, France","institution_ids":["https://openalex.org/I4210125985","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"LSIS UMR CNRS 6168, Universit\u00e9 d'Aix-Marseille, Domaine Universitaire de St Jer\u00f4me, F-13997, Marseille Cedex 20, France","institution_ids":["https://openalex.org/I1294671590"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5025426575"],"corresponding_institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I4210125985"],"apc_list":null,"apc_paid":null,"fwci":1.3874,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.87584097,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"5","issue":null,"first_page":"343","last_page":"352"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9997000098228455,"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":0.9997000098228455,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9959999918937683,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9958000183105469,"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/computer-science","display_name":"Computer science","score":0.8335111141204834},{"id":"https://openalex.org/keywords/ontology","display_name":"Ontology","score":0.6212496757507324},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6204482316970825},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.6116753816604614},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5734822154045105},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.5495558381080627},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.5279618501663208},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.5045527219772339},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.46040475368499756},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.45971065759658813},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.45956212282180786},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4528941512107849},{"id":"https://openalex.org/keywords/web-modeling","display_name":"Web modeling","score":0.4156322479248047}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8335111141204834},{"id":"https://openalex.org/C25810664","wikidata":"https://www.wikidata.org/wiki/Q44325","display_name":"Ontology","level":2,"score":0.6212496757507324},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6204482316970825},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.6116753816604614},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5734822154045105},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.5495558381080627},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.5279618501663208},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.5045527219772339},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.46040475368499756},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.45971065759658813},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.45956212282180786},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4528941512107849},{"id":"https://openalex.org/C130436687","wikidata":"https://www.wikidata.org/wiki/Q7978591","display_name":"Web modeling","level":3,"score":0.4156322479248047},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/rcis.2010.5507394","is_oa":false,"landing_page_url":"https://doi.org/10.1109/rcis.2010.5507394","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 Fourth International Conference on Research Challenges in Information Science (RCIS)","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":20,"referenced_works":["https://openalex.org/W168632859","https://openalex.org/W191178776","https://openalex.org/W200042785","https://openalex.org/W1966086923","https://openalex.org/W1986583960","https://openalex.org/W2058316166","https://openalex.org/W2127978399","https://openalex.org/W2147818521","https://openalex.org/W2150355486","https://openalex.org/W2151321914","https://openalex.org/W2154749666","https://openalex.org/W2156049581","https://openalex.org/W2421105961","https://openalex.org/W2505792640","https://openalex.org/W4285719527","https://openalex.org/W6606710655","https://openalex.org/W6607897444","https://openalex.org/W6608051331","https://openalex.org/W6681818278","https://openalex.org/W6682309673"],"related_works":["https://openalex.org/W36911888","https://openalex.org/W2137912379","https://openalex.org/W2120222276","https://openalex.org/W4385731361","https://openalex.org/W143181582","https://openalex.org/W3025289787","https://openalex.org/W2404573736","https://openalex.org/W2167278502","https://openalex.org/W2036104219","https://openalex.org/W2124649262"],"abstract_inverted_index":{"Web":[0],"is":[1,22],"growing":[2],"constantly":[3],"and":[4,76,100],"exponentially":[5],"every":[6],"day.":[7],"Thus,":[8],"gathering":[9,122],"relevant":[10],"information":[11,19,82,98,111,121],"becomes":[12],"unfeasible.":[13],"Existent":[14],"indexing-based":[15],"search":[16],"engines":[17],"ignore":[18],"context,":[20,46],"which":[21],"essential":[23],"to":[24,30,40,57,70,78],"deciding":[25],"on":[26,123],"its":[27,101],"relevance.":[28],"Restraining":[29],"a":[31,92,104,116],"single":[32],"web":[33,53,125],"domain,":[34],"domain":[35,60],"ontology":[36,69],"can":[37],"be":[38],"used":[39],"take":[41],"into":[42],"consideration":[43],"the":[44,47,58,107],"related":[45],"fact":[48],"that":[49,55,66],"might":[50],"enable":[51],"treating":[52],"pages":[54],"belong":[56],"considered":[59],"more":[61],"intelligently.":[62],"Nevertheless,":[63],"symbolic":[64,108],"rules":[65],"exploit":[67],"domain's":[68],"realize":[71],"this":[72],"treatment":[73],"are":[74],"delicate":[75],"fastidious":[77],"develop,":[79],"especially":[80],"for":[81,96,110,120],"extraction":[83,112],"task.":[84],"This":[85],"paper":[86],"presents":[87],"Boosted":[88],"Wrapper":[89],"Induction":[90],"(BWI),":[91],"machine":[93],"learning":[94],"method":[95],"adaptive":[97],"extraction,":[99],"exploitation":[102],"as":[103],"replacement":[105],"of":[106],"approach":[109],"task":[113],"in":[114],"AGATHE,":[115],"generic":[117],"multi-agent":[118],"architecture":[119],"restrained":[124],"domains.":[126]},"counts_by_year":[{"year":2016,"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"}
