{"id":"https://openalex.org/W1987680958","doi":"https://doi.org/10.1145/1031171.1031285","title":"Stemming and lemmatization in the clustering of finnish text documents","display_name":"Stemming and lemmatization in the clustering of finnish text documents","publication_year":2004,"publication_date":"2004-11-13","ids":{"openalex":"https://openalex.org/W1987680958","doi":"https://doi.org/10.1145/1031171.1031285","mag":"1987680958"},"language":"en","primary_location":{"id":"doi:10.1145/1031171.1031285","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1031171.1031285","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the thirteenth ACM international conference on Information and knowledge management","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/A5038345598","display_name":"Tuomo Korenius","orcid":null},"institutions":[{"id":"https://openalex.org/I166825849","display_name":"Tampere University","ror":"https://ror.org/033003e23","country_code":"FI","type":"education","lineage":["https://openalex.org/I166825849"]},{"id":"https://openalex.org/I4210133110","display_name":"Tampere University","ror":null,"country_code":"FI","type":null,"lineage":["https://openalex.org/I4210133110"]}],"countries":["FI"],"is_corresponding":true,"raw_author_name":"Tuomo Korenius","raw_affiliation_strings":["University of Tampere, Finland"],"affiliations":[{"raw_affiliation_string":"University of Tampere, Finland","institution_ids":["https://openalex.org/I166825849","https://openalex.org/I4210133110"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084187883","display_name":"Jorma Laurikkala","orcid":null},"institutions":[{"id":"https://openalex.org/I166825849","display_name":"Tampere University","ror":"https://ror.org/033003e23","country_code":"FI","type":"education","lineage":["https://openalex.org/I166825849"]},{"id":"https://openalex.org/I4210133110","display_name":"Tampere University","ror":null,"country_code":"FI","type":null,"lineage":["https://openalex.org/I4210133110"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Jorma Laurikkala","raw_affiliation_strings":["University of Tampere, Finland"],"affiliations":[{"raw_affiliation_string":"University of Tampere, Finland","institution_ids":["https://openalex.org/I166825849","https://openalex.org/I4210133110"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014374477","display_name":"Kalervo J\u00e4rvelin","orcid":"https://orcid.org/0000-0001-7655-8930"},"institutions":[{"id":"https://openalex.org/I166825849","display_name":"Tampere University","ror":"https://ror.org/033003e23","country_code":"FI","type":"education","lineage":["https://openalex.org/I166825849"]},{"id":"https://openalex.org/I4210133110","display_name":"Tampere University","ror":null,"country_code":"FI","type":null,"lineage":["https://openalex.org/I4210133110"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Kalervo J\u00e4rvelin","raw_affiliation_strings":["University of Tampere, Finland"],"affiliations":[{"raw_affiliation_string":"University of Tampere, Finland","institution_ids":["https://openalex.org/I166825849","https://openalex.org/I4210133110"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023021257","display_name":"Martti Juhola","orcid":"https://orcid.org/0000-0003-2298-9553"},"institutions":[{"id":"https://openalex.org/I166825849","display_name":"Tampere University","ror":"https://ror.org/033003e23","country_code":"FI","type":"education","lineage":["https://openalex.org/I166825849"]},{"id":"https://openalex.org/I4210133110","display_name":"Tampere University","ror":null,"country_code":"FI","type":null,"lineage":["https://openalex.org/I4210133110"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Martti Juhola","raw_affiliation_strings":["University of Tampere, Finland"],"affiliations":[{"raw_affiliation_string":"University of Tampere, Finland","institution_ids":["https://openalex.org/I166825849","https://openalex.org/I4210133110"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5038345598"],"corresponding_institution_ids":["https://openalex.org/I166825849","https://openalex.org/I4210133110"],"apc_list":null,"apc_paid":null,"fwci":4.6253,"has_fulltext":false,"cited_by_count":187,"citation_normalized_percentile":{"value":0.94490923,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"625","last_page":"633"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9991999864578247,"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/T10028","display_name":"Topic Modeling","score":0.9991999864578247,"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/T10181","display_name":"Natural Language Processing Techniques","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/T11719","display_name":"Data Quality and Management","score":0.9954000115394592,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/lemmatisation","display_name":"Lemmatisation","score":0.9842023849487305},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8062336444854736},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.7132745981216431},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.603995680809021},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5895928740501404},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.5390633344650269},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5223796963691711},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.42570969462394714}],"concepts":[{"id":"https://openalex.org/C161831844","wikidata":"https://www.wikidata.org/wiki/Q2554325","display_name":"Lemmatisation","level":2,"score":0.9842023849487305},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8062336444854736},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.7132745981216431},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.603995680809021},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5895928740501404},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.5390633344650269},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5223796963691711},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.42570969462394714},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/1031171.1031285","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1031171.1031285","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the thirteenth ACM international conference on Information and knowledge management","raw_type":"proceedings-article"},{"id":"pmh:oai:tampub.uta.fi:10024/66142","is_oa":false,"landing_page_url":"http://tampub.uta.fi/handle/10024/66142","pdf_url":null,"source":{"id":"https://openalex.org/S4306401860","display_name":"Tampere University Institutional Repository (Tampere University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I150589677","host_organization_name":"Tampere University of Applied Sciences","host_organization_lineage":["https://openalex.org/I150589677"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"","raw_type":"conferenceObject"},{"id":"pmh:oai:trepo.tuni.fi:10024/66142","is_oa":false,"landing_page_url":"https://trepo.tuni.fi/handle/10024/66142","pdf_url":null,"source":{"id":"https://openalex.org/S7407055260","display_name":"Trepo - Institutional Repository of Tampere University","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":null,"raw_type":"conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7200000286102295}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321108","display_name":"Academy of Finland","ror":"https://ror.org/05k73zm37"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W84158582","https://openalex.org/W119444765","https://openalex.org/W201288405","https://openalex.org/W1499177162","https://openalex.org/W1541096673","https://openalex.org/W1569899956","https://openalex.org/W1589845329","https://openalex.org/W1971285215","https://openalex.org/W1979076595","https://openalex.org/W1987748324","https://openalex.org/W1997841190","https://openalex.org/W2006477783","https://openalex.org/W2046732239","https://openalex.org/W2050879758","https://openalex.org/W2058200372","https://openalex.org/W2064262426","https://openalex.org/W2078455576","https://openalex.org/W2084849788","https://openalex.org/W2102270039","https://openalex.org/W2145036943","https://openalex.org/W2156296249","https://openalex.org/W2166972230","https://openalex.org/W2612166593","https://openalex.org/W2914866334","https://openalex.org/W4292023222","https://openalex.org/W6721827378"],"related_works":["https://openalex.org/W3124131622","https://openalex.org/W2970358562","https://openalex.org/W2513202451","https://openalex.org/W2795445283","https://openalex.org/W2285263069","https://openalex.org/W3190705690","https://openalex.org/W2575750760","https://openalex.org/W2056380474","https://openalex.org/W3198290408","https://openalex.org/W4385574727"],"abstract_inverted_index":{"Stemming":[0],"and":[1,18,65,92,116],"lemmatization":[2,88,110,125],"were":[3,46],"compared":[4],"in":[5],"the":[6,28,38,44,63,67,80,90,99,113],"clustering":[7,77],"of":[8,27,43],"Finnish":[9,13,135],"text":[10,136],"documents.":[11],"Since":[12],"is":[14,126],"a":[15,49,127],"highly":[16,68,100],"inflectional":[17],"agglutinative":[19],"language,":[20],"we":[21],"hypothesized":[22],"that":[23,87,124],"lemmatization,":[24],"involving":[25],"splitting":[26],"compound":[29],"words,":[30],"would":[31],"be":[32],"more":[33],"appropriate":[34],"normalization":[35,130],"approach":[36],"than":[37,104,132],"straightforward":[39],"stemming.":[40,105],"The":[41,82],"relevance":[42,51,84],"documents":[45,70,102,137],"evaluated":[47],"with":[48,74,108,112],"four-point":[50],"assessment":[52],"scale,":[53],"which":[54],"was":[55],"collapsed":[56],"into":[57],"binary":[58],"one":[59],"by":[60],"considering":[61],"all":[62],"relevant":[64,69,101],"only":[66],"relevant,":[71],"respectively.":[72],"Experiments":[73],"four":[75],"hierarchical":[76],"methods":[78,95,118],"supported":[79],"hypothesis.":[81],"stringent":[83],"scale":[85],"showed":[86],"allowed":[89],"single":[91],"complete":[93],"linkage":[94,115],"to":[96],"recover":[97],"especially":[98],"better":[103,128],"In":[106],"comparison":[107],"stemming,":[109,133],"together":[111],"average":[114],"Ward's":[117],"produced":[119],"higher":[120],"precision.":[121],"We":[122],"conclude":[123],"word":[129],"method":[131],"when":[134],"are":[138],"clustered":[139],"for":[140],"information":[141],"retrieval.":[142]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":13},{"year":2022,"cited_by_count":21},{"year":2021,"cited_by_count":17},{"year":2020,"cited_by_count":22},{"year":2019,"cited_by_count":12},{"year":2018,"cited_by_count":10},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":11},{"year":2015,"cited_by_count":11},{"year":2014,"cited_by_count":6},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":7}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
