{"id":"https://openalex.org/W2128808847","doi":"https://doi.org/10.1145/1529282.1529605","title":"Combining statistics and semantics via ensemble model for document clustering","display_name":"Combining statistics and semantics via ensemble model for document clustering","publication_year":2009,"publication_date":"2009-03-08","ids":{"openalex":"https://openalex.org/W2128808847","doi":"https://doi.org/10.1145/1529282.1529605","mag":"2128808847"},"language":"en","primary_location":{"id":"doi:10.1145/1529282.1529605","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1529282.1529605","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2009 ACM symposium on Applied Computing","raw_type":"proceedings-article"},"type":"conference-paper","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/A5025703949","display_name":"Samah Fodeh","orcid":"https://orcid.org/0000-0003-4664-3143"},"institutions":[{"id":"https://openalex.org/I87216513","display_name":"Michigan State University","ror":"https://ror.org/05hs6h993","country_code":"US","type":"education","lineage":["https://openalex.org/I87216513"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Samah Jamal Fodeh","raw_affiliation_strings":["Michigan State University, East Lansing, MI","Michigan State University East Lansing, MI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Michigan State University, East Lansing, MI","institution_ids":["https://openalex.org/I87216513"]},{"raw_affiliation_string":"Michigan State University East Lansing, MI","institution_ids":["https://openalex.org/I87216513"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089550786","display_name":"William F. Punch","orcid":null},"institutions":[{"id":"https://openalex.org/I87216513","display_name":"Michigan State University","ror":"https://ror.org/05hs6h993","country_code":"US","type":"education","lineage":["https://openalex.org/I87216513"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"William F Punch","raw_affiliation_strings":["Michigan State University, East Lansing, MI","Michigan State University East Lansing, MI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Michigan State University, East Lansing, MI","institution_ids":["https://openalex.org/I87216513"]},{"raw_affiliation_string":"Michigan State University East Lansing, MI","institution_ids":["https://openalex.org/I87216513"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071546444","display_name":"Pang\u2010Ning Tan","orcid":"https://orcid.org/0000-0003-3205-0339"},"institutions":[{"id":"https://openalex.org/I87216513","display_name":"Michigan State University","ror":"https://ror.org/05hs6h993","country_code":"US","type":"education","lineage":["https://openalex.org/I87216513"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pang-Ning Tan","raw_affiliation_strings":["Michigan State University, East Lansing, MI","Michigan State University East Lansing, MI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Michigan State University, East Lansing, MI","institution_ids":["https://openalex.org/I87216513"]},{"raw_affiliation_string":"Michigan State University East Lansing, MI","institution_ids":["https://openalex.org/I87216513"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I87216513"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1446","last_page":"1450"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9986000061035156,"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":0.9986000061035156,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9983000159263611,"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/T10028","display_name":"Topic Modeling","score":0.9969000220298767,"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/computer-science","display_name":"Computer science","score":0.8234339356422424},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6010592579841614},{"id":"https://openalex.org/keywords/wordnet","display_name":"WordNet","score":0.5861939191818237},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5861888527870178},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4869912564754486},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4748554229736328},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.41621050238609314},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.38205182552337646},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3492797613143921}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8234339356422424},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6010592579841614},{"id":"https://openalex.org/C157659113","wikidata":"https://www.wikidata.org/wiki/Q533822","display_name":"WordNet","level":2,"score":0.5861939191818237},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5861888527870178},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4869912564754486},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4748554229736328},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.41621050238609314},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.38205182552337646},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3492797613143921},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1529282.1529605","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1529282.1529605","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2009 ACM symposium on Applied Computing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.564.6333","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.564.6333","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.h-net.org/archive/documentation/combining statistics and semantics via ensemble model for document clustering.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6100000143051147,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320310016","display_name":"Michigan State University","ror":"https://ror.org/05hs6h993"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W2283060","https://openalex.org/W19599942","https://openalex.org/W100104462","https://openalex.org/W130742730","https://openalex.org/W1651093245","https://openalex.org/W1972978214","https://openalex.org/W1982024311","https://openalex.org/W2081580037","https://openalex.org/W2133517430","https://openalex.org/W2136480620","https://openalex.org/W2761554372"],"related_works":["https://openalex.org/W2900382651","https://openalex.org/W1981879262","https://openalex.org/W2363417484","https://openalex.org/W4225863708","https://openalex.org/W1599970036","https://openalex.org/W1480103567","https://openalex.org/W158852162","https://openalex.org/W2003651848","https://openalex.org/W1849827364","https://openalex.org/W2786299737"],"abstract_inverted_index":{"Incorporating":[0],"background":[1],"knowledge":[2,20,25],"into":[3],"data":[4,30,53,85],"mining":[5],"algorithms":[6],"is":[7,49,62],"an":[8,37],"important":[9],"but":[10],"challenging":[11],"problem.":[12],"Current":[13],"approaches":[14],"in":[15],"semi-supervised":[16],"learning":[17],"require":[18],"explicit":[19],"provided":[21],"by":[22],"domain":[23],"experts,":[24],"specific":[26],"to":[27,64],"the":[28,52,72,81],"particular":[29],"set.":[31],"In":[32],"this":[33],"study,":[34],"we":[35],"propose":[36],"ensemble":[38,78],"model":[39,79],"that":[40,48,61],"couples":[41],"two":[42],"sources":[43],"of":[44,74],"information:":[45],"statistics":[46],"information":[47,57],"derived":[50],"from":[51,59],"set,":[54],"and":[55,83],"sense":[56],"retrieved":[58],"WordNet":[60],"used":[63],"build":[65],"a":[66],"semantic":[67],"binary":[68],"model.":[69],"We":[70],"evaluated":[71],"efficacy":[73],"using":[75],"our":[76],"combined":[77],"on":[80],"Reuters-21578":[82],"20newsgroups":[84],"sets.":[86]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
