{"id":"https://openalex.org/W2142859716","doi":"https://doi.org/10.1007/978-3-642-19931-8_15","title":"Web Document Duplicate Detection Using Fuzzy Hashing","display_name":"Web Document Duplicate Detection Using Fuzzy Hashing","publication_year":2011,"publication_date":"2011-01-01","ids":{"openalex":"https://openalex.org/W2142859716","doi":"https://doi.org/10.1007/978-3-642-19931-8_15","mag":"2142859716"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-642-19931-8_15","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-642-19931-8_15","pdf_url":null,"source":{"id":"https://openalex.org/S4210208846","display_name":"Advances in intelligent and soft computing","issn_l":"1867-5662","issn":["1867-5662","1867-5670"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Intelligent and Soft Computing","raw_type":"book-chapter"},"type":"book-chapter","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/A5020867832","display_name":"Carlos G. Figuerola","orcid":"https://orcid.org/0000-0001-6799-2874"},"institutions":[{"id":"https://openalex.org/I184999862","display_name":"Universidad de Salamanca","ror":"https://ror.org/02f40zc51","country_code":"ES","type":"education","lineage":["https://openalex.org/I184999862"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Carlos G. Figuerola","raw_affiliation_strings":["University of Salamanca, C/ Francisco de Vitoria 6-16, 37008, Salamanca, Spain"],"affiliations":[{"raw_affiliation_string":"University of Salamanca, C/ Francisco de Vitoria 6-16, 37008, Salamanca, Spain","institution_ids":["https://openalex.org/I184999862"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002811242","display_name":"Raquel G\u00f3mez\u2010D\u00edaz","orcid":"https://orcid.org/0000-0002-1423-1315"},"institutions":[{"id":"https://openalex.org/I184999862","display_name":"Universidad de Salamanca","ror":"https://ror.org/02f40zc51","country_code":"ES","type":"education","lineage":["https://openalex.org/I184999862"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Raquel G\u00f3mez D\u00edaz","raw_affiliation_strings":["University of Salamanca, C/ Francisco de Vitoria 6-16, 37008, Salamanca, Spain"],"affiliations":[{"raw_affiliation_string":"University of Salamanca, C/ Francisco de Vitoria 6-16, 37008, Salamanca, Spain","institution_ids":["https://openalex.org/I184999862"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003362399","display_name":"Jos\u00e9 Lu\u00eds Alonso Berrocal","orcid":"https://orcid.org/0000-0001-7470-0091"},"institutions":[{"id":"https://openalex.org/I184999862","display_name":"Universidad de Salamanca","ror":"https://ror.org/02f40zc51","country_code":"ES","type":"education","lineage":["https://openalex.org/I184999862"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Jos\u00e9 L. Alonso Berrocal","raw_affiliation_strings":["University of Salamanca, C/ Francisco de Vitoria 6-16, 37008, Salamanca, Spain"],"affiliations":[{"raw_affiliation_string":"University of Salamanca, C/ Francisco de Vitoria 6-16, 37008, Salamanca, Spain","institution_ids":["https://openalex.org/I184999862"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038692240","display_name":"\u00c1ngel Francisco Zazo Rodr\u00edguez","orcid":"https://orcid.org/0000-0001-9385-1880"},"institutions":[{"id":"https://openalex.org/I184999862","display_name":"Universidad de Salamanca","ror":"https://ror.org/02f40zc51","country_code":"ES","type":"education","lineage":["https://openalex.org/I184999862"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Angel F. Zazo Rodr\u00edguez","raw_affiliation_strings":["University of Salamanca, C/ Francisco de Vitoria 6-16, 37008, Salamanca, Spain"],"affiliations":[{"raw_affiliation_string":"University of Salamanca, C/ Francisco de Vitoria 6-16, 37008, Salamanca, Spain","institution_ids":["https://openalex.org/I184999862"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5020867832"],"corresponding_institution_ids":["https://openalex.org/I184999862"],"apc_list":null,"apc_paid":null,"fwci":0.7354,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.78054407,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"117","last_page":"125"},"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/T11269","display_name":"Algorithms and Data Compression","score":0.9987999796867371,"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"}},{"id":"https://openalex.org/T11644","display_name":"Spam and Phishing Detection","score":0.9983000159263611,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8111940622329712},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.7968333959579468},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.658794641494751},{"id":"https://openalex.org/keywords/closeness","display_name":"Closeness","score":0.633078932762146},{"id":"https://openalex.org/keywords/disk-formatting","display_name":"Disk formatting","score":0.5735433101654053},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5002768039703369},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3824634850025177},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.32263749837875366}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8111940622329712},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.7968333959579468},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.658794641494751},{"id":"https://openalex.org/C2779545769","wikidata":"https://www.wikidata.org/wiki/Q5135364","display_name":"Closeness","level":2,"score":0.633078932762146},{"id":"https://openalex.org/C88006597","wikidata":"https://www.wikidata.org/wiki/Q690117","display_name":"Disk formatting","level":2,"score":0.5735433101654053},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5002768039703369},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3824634850025177},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.32263749837875366},{"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-3-642-19931-8_15","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-642-19931-8_15","pdf_url":null,"source":{"id":"https://openalex.org/S4210208846","display_name":"Advances in intelligent and soft computing","issn_l":"1867-5662","issn":["1867-5662","1867-5670"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Intelligent and Soft Computing","raw_type":"book-chapter"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W841409518","https://openalex.org/W1485982513","https://openalex.org/W1565377632","https://openalex.org/W1647671624","https://openalex.org/W1658906662","https://openalex.org/W1964478843","https://openalex.org/W1980073965","https://openalex.org/W1981981644","https://openalex.org/W1997438973","https://openalex.org/W2001496424","https://openalex.org/W2066792529","https://openalex.org/W2067432306","https://openalex.org/W2091340087","https://openalex.org/W2118342377","https://openalex.org/W2168154523","https://openalex.org/W2342204193","https://openalex.org/W2482589566","https://openalex.org/W4214671568","https://openalex.org/W6633894697"],"related_works":["https://openalex.org/W4244466418","https://openalex.org/W2104062382","https://openalex.org/W2162878363","https://openalex.org/W2389021890","https://openalex.org/W3023343521","https://openalex.org/W4245101192","https://openalex.org/W2146588098","https://openalex.org/W2479325685","https://openalex.org/W3183791698","https://openalex.org/W2480873127"],"abstract_inverted_index":null,"counts_by_year":[{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
