{"id":"https://openalex.org/W1529954983","doi":"https://doi.org/10.1007/978-3-642-00958-7_61","title":"Evaluation of Text Clustering Algorithms with N-Gram-Based Document Fingerprints","display_name":"Evaluation of Text Clustering Algorithms with N-Gram-Based Document Fingerprints","publication_year":2009,"publication_date":"2009-01-01","ids":{"openalex":"https://openalex.org/W1529954983","doi":"https://doi.org/10.1007/978-3-642-00958-7_61","mag":"1529954983"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-642-00958-7_61","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-642-00958-7_61","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"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":"Lecture Notes in Computer Science","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/A5046723532","display_name":"Javier Parapar","orcid":"https://orcid.org/0000-0002-5997-8252"},"institutions":[{"id":"https://openalex.org/I11019714","display_name":"Universidade da Coru\u00f1a","ror":"https://ror.org/01qckj285","country_code":"ES","type":"education","lineage":["https://openalex.org/I11019714"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Javier Parapar","raw_affiliation_strings":["IRLab, Computer Science Department, University of A Coru\u00f1a, Spain","IRLab., Computer Science Department, University of A Coru\u00f1a, Spain"],"affiliations":[{"raw_affiliation_string":"IRLab, Computer Science Department, University of A Coru\u00f1a, Spain","institution_ids":["https://openalex.org/I11019714"]},{"raw_affiliation_string":"IRLab., Computer Science Department, University of A Coru\u00f1a, Spain","institution_ids":["https://openalex.org/I11019714"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056469959","display_name":"\u00c1lvaro Barreiro","orcid":"https://orcid.org/0000-0002-6698-2946"},"institutions":[{"id":"https://openalex.org/I11019714","display_name":"Universidade da Coru\u00f1a","ror":"https://ror.org/01qckj285","country_code":"ES","type":"education","lineage":["https://openalex.org/I11019714"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"\u00c1lvaro Barreiro","raw_affiliation_strings":["IRLab, Computer Science Department, University of A Coru\u00f1a, Spain","IRLab., Computer Science Department, University of A Coru\u00f1a, Spain"],"affiliations":[{"raw_affiliation_string":"IRLab, Computer Science Department, University of A Coru\u00f1a, Spain","institution_ids":["https://openalex.org/I11019714"]},{"raw_affiliation_string":"IRLab., Computer Science Department, University of A Coru\u00f1a, Spain","institution_ids":["https://openalex.org/I11019714"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5046723532"],"corresponding_institution_ids":["https://openalex.org/I11019714"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":0.8657,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.73505485,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"645","last_page":"653"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9997000098228455,"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"}},"topics":[{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9997000098228455,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9896000027656555,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9861999750137329,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.8643901944160461},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7901028394699097},{"id":"https://openalex.org/keywords/trimming","display_name":"Trimming","score":0.7716817259788513},{"id":"https://openalex.org/keywords/n-gram","display_name":"n-gram","score":0.6410566568374634},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5866858959197998},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5646018981933594},{"id":"https://openalex.org/keywords/document-clustering","display_name":"Document clustering","score":0.5292142033576965},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4368003308773041},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2791494131088257},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.07742121815681458}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8643901944160461},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7901028394699097},{"id":"https://openalex.org/C56951928","wikidata":"https://www.wikidata.org/wiki/Q3539213","display_name":"Trimming","level":2,"score":0.7716817259788513},{"id":"https://openalex.org/C117884012","wikidata":"https://www.wikidata.org/wiki/Q94489","display_name":"n-gram","level":3,"score":0.6410566568374634},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5866858959197998},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5646018981933594},{"id":"https://openalex.org/C177937566","wikidata":"https://www.wikidata.org/wiki/Q4223102","display_name":"Document clustering","level":3,"score":0.5292142033576965},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4368003308773041},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2791494131088257},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.07742121815681458},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/978-3-642-00958-7_61","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-642-00958-7_61","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"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":"Lecture Notes in Computer Science","raw_type":"book-chapter"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.218.3317","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.218.3317","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.dc.fi.udc.es/~barreiro/publications/parapar_barreiro_ecir2009.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.550000011920929}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W260234060","https://openalex.org/W370143576","https://openalex.org/W1972418517","https://openalex.org/W1992419399","https://openalex.org/W1996764654","https://openalex.org/W1997611468","https://openalex.org/W2005191276","https://openalex.org/W2079306104","https://openalex.org/W2103986443","https://openalex.org/W2107593949","https://openalex.org/W2111295912","https://openalex.org/W2127218421","https://openalex.org/W2130395434","https://openalex.org/W2152565070","https://openalex.org/W2736765627","https://openalex.org/W2912431181","https://openalex.org/W2916086000","https://openalex.org/W3142746689","https://openalex.org/W3145042860","https://openalex.org/W4235395760"],"related_works":["https://openalex.org/W2467235537","https://openalex.org/W1493074871","https://openalex.org/W1795405792","https://openalex.org/W2899601636","https://openalex.org/W4254379378","https://openalex.org/W4206655101","https://openalex.org/W52853789","https://openalex.org/W4237592971","https://openalex.org/W2387982377","https://openalex.org/W4322720815"],"abstract_inverted_index":null,"counts_by_year":[{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
