{"id":"https://openalex.org/W2158952869","doi":"https://doi.org/10.1145/1081870.1081957","title":"A hybrid unsupervised approach for document clustering","display_name":"A hybrid unsupervised approach for document clustering","publication_year":2005,"publication_date":"2005-08-21","ids":{"openalex":"https://openalex.org/W2158952869","doi":"https://doi.org/10.1145/1081870.1081957","mag":"2158952869"},"language":"en","primary_location":{"id":"doi:10.1145/1081870.1081957","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1081870.1081957","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the eleventh ACM SIGKDD international conference on Knowledge discovery in data mining","raw_type":"proceedings-article"},"type":"article","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/A5047699502","display_name":"Mihai Surdeanu","orcid":"https://orcid.org/0000-0001-6956-8030"},"institutions":[{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"education","lineage":["https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Mihai Surdeanu","raw_affiliation_strings":["Technical University of Catalonia, Barcelona, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University of Catalonia, Barcelona, Spain","institution_ids":["https://openalex.org/I9617848"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113960229","display_name":"Jordi Turmo","orcid":"https://orcid.org/0000-0002-7521-1115"},"institutions":[{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"education","lineage":["https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Jordi Turmo","raw_affiliation_strings":["Technical University of Catalonia, Barcelona, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University of Catalonia, Barcelona, Spain","institution_ids":["https://openalex.org/I9617848"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042954679","display_name":"Alicia Ageno","orcid":"https://orcid.org/0000-0003-2210-8082"},"institutions":[{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"education","lineage":["https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Alicia Ageno","raw_affiliation_strings":["Technical University of Catalonia, Barcelona, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University of Catalonia, Barcelona, Spain","institution_ids":["https://openalex.org/I9617848"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I9617848"],"apc_list":null,"apc_paid":null,"fwci":5.0586,"has_fulltext":false,"cited_by_count":37,"citation_normalized_percentile":{"value":0.95287141,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"685","last_page":"690"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9991000294685364,"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/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9991000294685364,"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":0.9991000294685364,"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"}},{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9991000294685364,"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/cluster-analysis","display_name":"Cluster analysis","score":0.8301851153373718},{"id":"https://openalex.org/keywords/initialization","display_name":"Initialization","score":0.7738684415817261},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7624382376670837},{"id":"https://openalex.org/keywords/expectation\u2013maximization-algorithm","display_name":"Expectation\u2013maximization algorithm","score":0.6094623804092407},{"id":"https://openalex.org/keywords/canopy-clustering-algorithm","display_name":"Canopy clustering algorithm","score":0.5982179641723633},{"id":"https://openalex.org/keywords/cure-data-clustering-algorithm","display_name":"CURE data clustering algorithm","score":0.560460090637207},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.5463583469390869},{"id":"https://openalex.org/keywords/correlation-clustering","display_name":"Correlation clustering","score":0.5301331877708435},{"id":"https://openalex.org/keywords/single-linkage-clustering","display_name":"Single-linkage clustering","score":0.5284512042999268},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5107212066650391},{"id":"https://openalex.org/keywords/dimension","display_name":"Dimension (graph theory)","score":0.4717365503311157},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.46896520256996155},{"id":"https://openalex.org/keywords/data-stream-clustering","display_name":"Data stream clustering","score":0.4597942531108856},{"id":"https://openalex.org/keywords/document-clustering","display_name":"Document clustering","score":0.41309744119644165},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38377729058265686},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3394169807434082},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1448829174041748},{"id":"https://openalex.org/keywords/maximum-likelihood","display_name":"Maximum likelihood","score":0.14338311553001404}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.8301851153373718},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.7738684415817261},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7624382376670837},{"id":"https://openalex.org/C182081679","wikidata":"https://www.wikidata.org/wiki/Q1275153","display_name":"Expectation\u2013maximization algorithm","level":3,"score":0.6094623804092407},{"id":"https://openalex.org/C104047586","wikidata":"https://www.wikidata.org/wiki/Q5033439","display_name":"Canopy clustering algorithm","level":4,"score":0.5982179641723633},{"id":"https://openalex.org/C33704608","wikidata":"https://www.wikidata.org/wiki/Q5014717","display_name":"CURE data clustering algorithm","level":4,"score":0.560460090637207},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.5463583469390869},{"id":"https://openalex.org/C94641424","wikidata":"https://www.wikidata.org/wiki/Q5172845","display_name":"Correlation clustering","level":3,"score":0.5301331877708435},{"id":"https://openalex.org/C22648726","wikidata":"https://www.wikidata.org/wiki/Q7523744","display_name":"Single-linkage clustering","level":5,"score":0.5284512042999268},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5107212066650391},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.4717365503311157},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.46896520256996155},{"id":"https://openalex.org/C193143536","wikidata":"https://www.wikidata.org/wiki/Q5227360","display_name":"Data stream clustering","level":5,"score":0.4597942531108856},{"id":"https://openalex.org/C177937566","wikidata":"https://www.wikidata.org/wiki/Q4223102","display_name":"Document clustering","level":3,"score":0.41309744119644165},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38377729058265686},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3394169807434082},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1448829174041748},{"id":"https://openalex.org/C49781872","wikidata":"https://www.wikidata.org/wiki/Q1045555","display_name":"Maximum likelihood","level":2,"score":0.14338311553001404},{"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/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1081870.1081957","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1081870.1081957","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the eleventh ACM SIGKDD international conference on Knowledge discovery in data mining","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.101.6654","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.101.6654","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.lsi.upc.edu/~ageno/kdd05.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W191422183","https://openalex.org/W1971318281","https://openalex.org/W1975152892","https://openalex.org/W2049633694","https://openalex.org/W2085487226","https://openalex.org/W2087962968","https://openalex.org/W2097089247","https://openalex.org/W2124634352","https://openalex.org/W2127042504","https://openalex.org/W2168175751","https://openalex.org/W2544694413","https://openalex.org/W2800394774","https://openalex.org/W3017143921","https://openalex.org/W4242401062","https://openalex.org/W6672191126","https://openalex.org/W6776565550"],"related_works":["https://openalex.org/W2160785859","https://openalex.org/W2188840951","https://openalex.org/W2559422900","https://openalex.org/W3120229345","https://openalex.org/W3140018618","https://openalex.org/W2374506950","https://openalex.org/W2352139139","https://openalex.org/W2393707058","https://openalex.org/W2622412490","https://openalex.org/W2770741777"],"abstract_inverted_index":{"We":[0,17,73],"propose":[1],"a":[2,10,24],"hybrid,":[3],"unsupervised":[4],"document":[5,82],"clustering":[6,12,91],"approach":[7,89],"that":[8,87],"combines":[9],"hierarchical":[11],"algorithm":[13,33,45,56],"with":[14],"Expectation":[15],"Maximization.":[16],"developed":[18],"several":[19],"heuristics":[20],"to":[21],"automatically":[22],"select":[23],"subset":[25],"of":[26,38,61,70,93],"the":[27,31,35,39,53,62,76],"clusters":[28],"generated":[29],"by":[30],"first":[32],"as":[34],"initial":[36,50],"points":[37],"second":[40],"one.":[41],"Furthermore,":[42],"our":[43,88],"initialization":[44],"generates":[46,90],"not":[47],"only":[48],"an":[49,59],"model":[51,63],"for":[52],"iterative":[54],"refinement":[55],"but":[57],"also":[58],"estimate":[60],"dimension,":[64],"thus":[65],"eliminating":[66],"another":[67],"important":[68],"element":[69],"human":[71],"supervision.":[72],"have":[74],"evaluated":[75],"proposed":[77],"system":[78],"on":[79],"five":[80],"real-world":[81],"collections.":[83],"The":[84],"results":[85],"show":[86],"solutions":[92],"higher":[94],"quality":[95],"than":[96],"both":[97],"its":[98],"individual":[99],"components.":[100]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":6}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}