{"id":"https://openalex.org/W2611540330","doi":"https://doi.org/10.1145/3066911.3066912","title":"Ontology-based approach for unsupervised and adaptive focused crawling","display_name":"Ontology-based approach for unsupervised and adaptive focused crawling","publication_year":2017,"publication_date":"2017-05-01","ids":{"openalex":"https://openalex.org/W2611540330","doi":"https://doi.org/10.1145/3066911.3066912","mag":"2611540330"},"language":"en","primary_location":{"id":"doi:10.1145/3066911.3066912","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3066911.3066912","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of The International Workshop on Semantic Big Data","raw_type":"proceedings-article"},"type":"preprint","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/A5102238918","display_name":"Thomas Hassan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210118524","display_name":"Universit\u00e9 Bourgogne Franche-Comt\u00e9","ror":"https://ror.org/02dn7x778","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210118524"]},{"id":"https://openalex.org/I4210136953","display_name":"Laboratoire d\u2019\u00c9lectronique, Informatique et Image","ror":"https://ror.org/04gnd7c94","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I190752583","https://openalex.org/I190861549","https://openalex.org/I4210118524","https://openalex.org/I4210134562","https://openalex.org/I4210136953","https://openalex.org/I4210159245"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Thomas Hassan","raw_affiliation_strings":["Univ. Bourgogne Franche-Comt\u00e9, Dijon, France","Le2i - Laboratoire d'Electronique, d'Informatique et d'Image [EA 7508] (9 Avenue Alain Savary - 21078 DIJON CEDEX - France)"],"affiliations":[{"raw_affiliation_string":"Univ. Bourgogne Franche-Comt\u00e9, Dijon, France","institution_ids":["https://openalex.org/I4210118524"]},{"raw_affiliation_string":"Le2i - Laboratoire d'Electronique, d'Informatique et d'Image [EA 7508] (9 Avenue Alain Savary - 21078 DIJON CEDEX - France)","institution_ids":["https://openalex.org/I4210136953"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031830209","display_name":"Christophe Cruz","orcid":"https://orcid.org/0000-0002-5611-9479"},"institutions":[{"id":"https://openalex.org/I4210118524","display_name":"Universit\u00e9 Bourgogne Franche-Comt\u00e9","ror":"https://ror.org/02dn7x778","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210118524"]},{"id":"https://openalex.org/I4210136953","display_name":"Laboratoire d\u2019\u00c9lectronique, Informatique et Image","ror":"https://ror.org/04gnd7c94","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I190752583","https://openalex.org/I190861549","https://openalex.org/I4210118524","https://openalex.org/I4210134562","https://openalex.org/I4210136953","https://openalex.org/I4210159245"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Christophe Cruz","raw_affiliation_strings":["Univ. Bourgogne Franche-Comt\u00e9, Dijon, France","Le2i - Laboratoire d'Electronique, d'Informatique et d'Image [EA 7508] (9 Avenue Alain Savary - 21078 DIJON CEDEX - France)"],"affiliations":[{"raw_affiliation_string":"Univ. Bourgogne Franche-Comt\u00e9, Dijon, France","institution_ids":["https://openalex.org/I4210118524"]},{"raw_affiliation_string":"Le2i - Laboratoire d'Electronique, d'Informatique et d'Image [EA 7508] (9 Avenue Alain Savary - 21078 DIJON CEDEX - France)","institution_ids":["https://openalex.org/I4210136953"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088285849","display_name":"Aur\u00e9lie Bertaux","orcid":null},"institutions":[{"id":"https://openalex.org/I4210136953","display_name":"Laboratoire d\u2019\u00c9lectronique, Informatique et Image","ror":"https://ror.org/04gnd7c94","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I190752583","https://openalex.org/I190861549","https://openalex.org/I4210118524","https://openalex.org/I4210134562","https://openalex.org/I4210136953","https://openalex.org/I4210159245"]},{"id":"https://openalex.org/I4210118524","display_name":"Universit\u00e9 Bourgogne Franche-Comt\u00e9","ror":"https://ror.org/02dn7x778","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210118524"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Aur\u00e9lie Bertaux","raw_affiliation_strings":["Univ. Bourgogne Franche-Comt\u00e9, Dijon, France","Le2i - Laboratoire d'Electronique, d'Informatique et d'Image [EA 7508] (9 Avenue Alain Savary - 21078 DIJON CEDEX - France)"],"affiliations":[{"raw_affiliation_string":"Univ. Bourgogne Franche-Comt\u00e9, Dijon, France","institution_ids":["https://openalex.org/I4210118524"]},{"raw_affiliation_string":"Le2i - Laboratoire d'Electronique, d'Informatique et d'Image [EA 7508] (9 Avenue Alain Savary - 21078 DIJON CEDEX - France)","institution_ids":["https://openalex.org/I4210136953"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5102238918"],"corresponding_institution_ids":["https://openalex.org/I4210118524","https://openalex.org/I4210136953"],"apc_list":null,"apc_paid":null,"fwci":4.47853631,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.94257029,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9531999826431274,"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/T11106","display_name":"Data Management and Algorithms","score":0.9376999735832214,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.8142355680465698},{"id":"https://openalex.org/keywords/ontology","display_name":"Ontology","score":0.6263436079025269},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5620138049125671},{"id":"https://openalex.org/keywords/semantic-web","display_name":"Semantic Web","score":0.5470666289329529},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5148800611495972},{"id":"https://openalex.org/keywords/crawling","display_name":"Crawling","score":0.47957557439804077},{"id":"https://openalex.org/keywords/web-crawler","display_name":"Web crawler","score":0.4614907503128052},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4510001540184021},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.45032042264938354},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.4122687876224518},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4014187455177307},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33577293157577515},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.33170023560523987},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.258394718170166}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8142355680465698},{"id":"https://openalex.org/C25810664","wikidata":"https://www.wikidata.org/wiki/Q44325","display_name":"Ontology","level":2,"score":0.6263436079025269},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5620138049125671},{"id":"https://openalex.org/C2129575","wikidata":"https://www.wikidata.org/wiki/Q54837","display_name":"Semantic Web","level":2,"score":0.5470666289329529},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5148800611495972},{"id":"https://openalex.org/C100368936","wikidata":"https://www.wikidata.org/wiki/Q1411725","display_name":"Crawling","level":2,"score":0.47957557439804077},{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.4614907503128052},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4510001540184021},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.45032042264938354},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.4122687876224518},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4014187455177307},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33577293157577515},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.33170023560523987},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.258394718170166},{"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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C105702510","wikidata":"https://www.wikidata.org/wiki/Q514","display_name":"Anatomy","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3066911.3066912","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3066911.3066912","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of The International Workshop on Semantic Big Data","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-01564206v1","is_oa":false,"landing_page_url":"https://ube.hal.science/hal-01564206","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://dl.acm.org/citation.cfm?doid=3066911.3066912","raw_type":"Conference papers"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320335322","display_name":"European Regional Development Fund","ror":"https://ror.org/00k4n6c32"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1489992655","https://openalex.org/W2017224880","https://openalex.org/W2038643757","https://openalex.org/W2058512949","https://openalex.org/W2064483469","https://openalex.org/W2119426258","https://openalex.org/W2124673015","https://openalex.org/W2130221750","https://openalex.org/W2136600545","https://openalex.org/W2140735141","https://openalex.org/W2164614639","https://openalex.org/W2168386304","https://openalex.org/W2171686321","https://openalex.org/W2188459837","https://openalex.org/W2509477067","https://openalex.org/W4300242129"],"related_works":["https://openalex.org/W3119324922","https://openalex.org/W2352686120","https://openalex.org/W2372594123","https://openalex.org/W2358310581","https://openalex.org/W2026132847","https://openalex.org/W4385695127","https://openalex.org/W2137810919","https://openalex.org/W2964752624","https://openalex.org/W4255854114","https://openalex.org/W2026661369"],"abstract_inverted_index":{"International":[0],"audience":[1]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2017-05-12T00:00:00"}
