{"id":"https://openalex.org/W105881653","doi":"https://doi.org/10.1007/978-3-540-24630-5_64","title":"Filtering Very Similar Text Documents: A Case Study","display_name":"Filtering Very Similar Text Documents: A Case Study","publication_year":2004,"publication_date":"2004-01-01","ids":{"openalex":"https://openalex.org/W105881653","doi":"https://doi.org/10.1007/978-3-540-24630-5_64","mag":"105881653"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-540-24630-5_64","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-540-24630-5_64","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/A5025936831","display_name":"Ji\u0159\u00ed Hroza","orcid":null},"institutions":[{"id":"https://openalex.org/I21449261","display_name":"Masaryk University","ror":"https://ror.org/02j46qs45","country_code":"CZ","type":"education","lineage":["https://openalex.org/I21449261"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Ji\u0159\u00ed Hroza","raw_affiliation_strings":["Faculty of Informatics, Department of Information Technologies, Masaryk University, Botanick\u00e1 68a, 602 00, Brno, Czech Republic"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Informatics, Department of Information Technologies, Masaryk University, Botanick\u00e1 68a, 602 00, Brno, Czech Republic","institution_ids":["https://openalex.org/I21449261"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011508990","display_name":"J\u00e1n \u017di\u017eka","orcid":"https://orcid.org/0000-0002-8035-0144"},"institutions":[{"id":"https://openalex.org/I21449261","display_name":"Masaryk University","ror":"https://ror.org/02j46qs45","country_code":"CZ","type":"education","lineage":["https://openalex.org/I21449261"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Jan \u017di\u017eka","raw_affiliation_strings":["Faculty of Informatics, Department of Information Technologies, Masaryk University, Botanick\u00e1 68a, 602 00, Brno, Czech Republic"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Informatics, Department of Information Technologies, Masaryk University, Botanick\u00e1 68a, 602 00, Brno, Czech Republic","institution_ids":["https://openalex.org/I21449261"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044193854","display_name":"Ale\u0161 Bourek","orcid":null},"institutions":[{"id":"https://openalex.org/I21449261","display_name":"Masaryk University","ror":"https://ror.org/02j46qs45","country_code":"CZ","type":"education","lineage":["https://openalex.org/I21449261"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Ale\u0161 Bourek","raw_affiliation_strings":["Faculty of Medicine, Department of Biophysics, Masaryk University, Jo\u0161tova 10, 662 43, Brno, Czech Republic"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Medicine, Department of Biophysics, Masaryk University, Jo\u0161tova 10, 662 43, Brno, Czech Republic","institution_ids":["https://openalex.org/I21449261"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":0.2316,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.48134036,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"511","last_page":"520"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9995999932289124,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9995999932289124,"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":0.9979000091552734,"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/T10028","display_name":"Topic Modeling","score":0.9975000023841858,"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/similarity","display_name":"Similarity (geometry)","score":0.7836143970489502},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6933924555778503},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5934762954711914},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.5538460612297058},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.5510863661766052},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.49808216094970703},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4942953586578369},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.47599661350250244},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4740424156188965},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.4306792616844177},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.39823341369628906},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3556536138057709},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33066222071647644},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.20007815957069397},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.117399662733078}],"concepts":[{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.7836143970489502},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6933924555778503},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5934762954711914},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.5538460612297058},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.5510863661766052},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.49808216094970703},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4942953586578369},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.47599661350250244},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4740424156188965},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.4306792616844177},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.39823341369628906},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3556536138057709},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33066222071647644},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.20007815957069397},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.117399662733078},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-3-540-24630-5_64","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-540-24630-5_64","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W1501380136","https://openalex.org/W1553163567","https://openalex.org/W1554600341","https://openalex.org/W1576592193","https://openalex.org/W1651266083","https://openalex.org/W1966280301","https://openalex.org/W2098162425","https://openalex.org/W2118020653","https://openalex.org/W2426031434","https://openalex.org/W4285719527","https://openalex.org/W6648725293"],"related_works":["https://openalex.org/W2090763504","https://openalex.org/W148178222","https://openalex.org/W2104657898","https://openalex.org/W1948992892","https://openalex.org/W1886884218","https://openalex.org/W1910826599","https://openalex.org/W1980100242","https://openalex.org/W2530420969","https://openalex.org/W2051187167","https://openalex.org/W2327130486"],"abstract_inverted_index":null,"counts_by_year":[{"year":2014,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
