{"id":"https://openalex.org/W2737752454","doi":"https://doi.org/10.1145/3102254.3102291","title":"Integration of deep web sources","display_name":"Integration of deep web sources","publication_year":2017,"publication_date":"2017-06-19","ids":{"openalex":"https://openalex.org/W2737752454","doi":"https://doi.org/10.1145/3102254.3102291","mag":"2737752454"},"language":"en","primary_location":{"id":"doi:10.1145/3102254.3102291","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3102254.3102291","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th International Conference on Web Intelligence, Mining and Semantics","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://openportal.isti.cnr.it/doc?id=people______::f1b9819a0ec25e6409b38b7eaec139c3","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5007649727","display_name":"Andrea Cal\u0131\u0300","orcid":"https://orcid.org/0000-0001-5678-6899"},"institutions":[{"id":"https://openalex.org/I124357947","display_name":"University of London","ror":"https://ror.org/04cw6st05","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947"]},{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Andrea Cal\u00ec","raw_affiliation_strings":["Univ. of London and Univ. of Oxford, UK"],"affiliations":[{"raw_affiliation_string":"Univ. of London and Univ. of Oxford, UK","institution_ids":["https://openalex.org/I40120149","https://openalex.org/I124357947"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021966059","display_name":"Umberto Straccia","orcid":"https://orcid.org/0000-0001-5998-6757"},"institutions":[{"id":"https://openalex.org/I4210107558","display_name":"Consorzio Pisa Ricerche","ror":"https://ror.org/01t0n3b84","country_code":"IT","type":"facility","lineage":["https://openalex.org/I4210107558"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Umberto Straccia","raw_affiliation_strings":["Consiglio Nazionale delle Ricerche, Pisa, Italy"],"affiliations":[{"raw_affiliation_string":"Consiglio Nazionale delle Ricerche, Pisa, Italy","institution_ids":["https://openalex.org/I4210107558"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5007649727"],"corresponding_institution_ids":["https://openalex.org/I124357947","https://openalex.org/I40120149"],"apc_list":null,"apc_paid":null,"fwci":0.5059,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.74294219,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9998000264167786,"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":0.9998000264167786,"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/T11986","display_name":"Scientific Computing and Data Management","score":0.98580002784729,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9824000000953674,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/deep-web","display_name":"Deep Web","score":0.8759735822677612},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8555348515510559},{"id":"https://openalex.org/keywords/schema","display_name":"Schema (genetic algorithms)","score":0.6949910521507263},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6533005833625793},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.46788209676742554},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.40356940031051636},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3569992184638977},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.28843480348587036}],"concepts":[{"id":"https://openalex.org/C46721378","wikidata":"https://www.wikidata.org/wiki/Q221989","display_name":"Deep Web","level":3,"score":0.8759735822677612},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8555348515510559},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.6949910521507263},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6533005833625793},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.46788209676742554},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.40356940031051636},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3569992184638977},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.28843480348587036}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3102254.3102291","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3102254.3102291","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th International Conference on Web Intelligence, Mining and Semantics","raw_type":"proceedings-article"},{"id":"pmh:oai:dnet:people______::f1b9819a0ec25e6409b38b7eaec139c3","is_oa":true,"landing_page_url":"https://openportal.isti.cnr.it/doc?id=people______::f1b9819a0ec25e6409b38b7eaec139c3","pdf_url":null,"source":{"id":"https://openalex.org/S7407055261","display_name":"ISTI Open Portal","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"7th International Conference on Web Intelligence, Mining and Semantics (WIMS-17), pp. 33:1\u201333:4, 19-22 June 2017","raw_type":"Conference article"}],"best_oa_location":{"id":"pmh:oai:dnet:people______::f1b9819a0ec25e6409b38b7eaec139c3","is_oa":true,"landing_page_url":"https://openportal.isti.cnr.it/doc?id=people______::f1b9819a0ec25e6409b38b7eaec139c3","pdf_url":null,"source":{"id":"https://openalex.org/S7407055261","display_name":"ISTI Open Portal","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"7th International Conference on Web Intelligence, Mining and Semantics (WIMS-17), pp. 33:1\u201333:4, 19-22 June 2017","raw_type":"Conference article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5799999833106995,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G5141627942","display_name":null,"funder_award_id":"EP/L003260/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1589374951","https://openalex.org/W1959529172","https://openalex.org/W1977515256","https://openalex.org/W1984152712","https://openalex.org/W1986828474","https://openalex.org/W1992673035","https://openalex.org/W2005066702","https://openalex.org/W2009018050","https://openalex.org/W2023624732","https://openalex.org/W2031888594","https://openalex.org/W2037176899","https://openalex.org/W2042441172","https://openalex.org/W2099264454","https://openalex.org/W2113570274","https://openalex.org/W2115701094","https://openalex.org/W2116554599","https://openalex.org/W2126035644","https://openalex.org/W2132235885","https://openalex.org/W2145396905","https://openalex.org/W2148096737","https://openalex.org/W2161787409","https://openalex.org/W2168661392","https://openalex.org/W2340309946","https://openalex.org/W3031684986","https://openalex.org/W3101483322","https://openalex.org/W6611257893","https://openalex.org/W7065170726"],"related_works":["https://openalex.org/W2037906003","https://openalex.org/W4378699829","https://openalex.org/W2953265498","https://openalex.org/W2533455610","https://openalex.org/W4248236804","https://openalex.org/W2000745862","https://openalex.org/W1892772476","https://openalex.org/W2074888472","https://openalex.org/W2160189941","https://openalex.org/W2182622516"],"abstract_inverted_index":{"The":[0],"Deep":[1,20,52,109],"Web":[2,21,53,110],"consists":[3],"of":[4,57,87,92,108],"those":[5],"structured":[6],"data":[7],"that":[8,42,61],"are":[9,30],"available":[10],"as":[11,112,114],"dynamically":[12],"generated":[13],"pages,":[14],"typically":[15],"requested":[16],"through":[17],"HTML":[18],"forms.":[19],"pages":[22],"cannot":[23],"be":[24],"indexed":[25],"by":[26,55],"search":[27],"engines,":[28],"and":[29,35,106],"notoriously":[31],"difficult":[32],"to":[33,38,70,73,101],"query":[34],"integrate":[36],"due":[37],"the":[39,63,77,85,90],"limited":[40],"access":[41],"they":[43],"offer.":[44],"We":[45,96],"propose":[46,84],"a":[47,58,98,115],"novel":[48,99],"framework":[49],"for":[50,117],"integrating":[51],"sources":[54],"means":[56],"mediated":[59,78],"schema":[60],"represent":[62],"underlying,":[64],"distributed":[65],"sources.":[66],"Our":[67],"goal":[68],"is":[69],"compute":[71],"answers":[72],"queries":[74],"posed":[75],"on":[76],"schema.":[79],"To":[80],"this":[81],"aim,":[82],"we":[83],"use":[86],"techniques":[88],"from":[89],"area":[91],"Distributed":[93],"Information":[94],"Retrieval.":[95],"discuss":[97],"approach":[100],"automated":[102],"sampling,":[103],"size":[104],"estimation":[105],"selection":[107],"sources,":[111],"well":[113],"technique":[116],"merging":[118],"result":[119],"lists.":[120]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2026-04-24T08:23:43.765630","created_date":"2025-10-10T00:00:00"}
