{"id":"https://openalex.org/W2061749149","doi":"https://doi.org/10.1145/1816123.1816196","title":"Text clustering with important words using normalization","display_name":"Text clustering with important words using normalization","publication_year":2010,"publication_date":"2010-06-21","ids":{"openalex":"https://openalex.org/W2061749149","doi":"https://doi.org/10.1145/1816123.1816196","mag":"2061749149"},"language":"en","primary_location":{"id":"doi:10.1145/1816123.1816196","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1816123.1816196","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 10th annual joint conference on Digital libraries","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/A5070863501","display_name":"Shunyao Wu","orcid":"https://orcid.org/0000-0001-7774-9261"},"institutions":[{"id":"https://openalex.org/I44468530","display_name":"Qingdao University of Technology","ror":"https://ror.org/01qzc0f54","country_code":"CN","type":"education","lineage":["https://openalex.org/I44468530"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Shunyao Wu","raw_affiliation_strings":["Qingdao Technological University, Qingdao, China"],"affiliations":[{"raw_affiliation_string":"Qingdao Technological University, Qingdao, China","institution_ids":["https://openalex.org/I44468530"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100340094","display_name":"Jinlong Wang","orcid":"https://orcid.org/0000-0001-5679-1495"},"institutions":[{"id":"https://openalex.org/I44468530","display_name":"Qingdao University of Technology","ror":"https://ror.org/01qzc0f54","country_code":"CN","type":"education","lineage":["https://openalex.org/I44468530"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinlong Wang","raw_affiliation_strings":["Qingdao Technological University, Qingdao, China"],"affiliations":[{"raw_affiliation_string":"Qingdao Technological University, Qingdao, China","institution_ids":["https://openalex.org/I44468530"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027376496","display_name":"Huy Quan Vu","orcid":"https://orcid.org/0000-0003-1947-2879"},"institutions":[{"id":"https://openalex.org/I149704539","display_name":"Deakin University","ror":"https://ror.org/02czsnj07","country_code":"AU","type":"education","lineage":["https://openalex.org/I149704539"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Huy Quan Vu","raw_affiliation_strings":["Deakin University, Victoria, Australia","(Deakin University, Victoria, Australia)"],"affiliations":[{"raw_affiliation_string":"Deakin University, Victoria, Australia","institution_ids":["https://openalex.org/I149704539"]},{"raw_affiliation_string":"(Deakin University, Victoria, Australia)","institution_ids":["https://openalex.org/I149704539"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100438769","display_name":"Gang Li","orcid":"https://orcid.org/0000-0003-1583-641X"},"institutions":[{"id":"https://openalex.org/I149704539","display_name":"Deakin University","ror":"https://ror.org/02czsnj07","country_code":"AU","type":"education","lineage":["https://openalex.org/I149704539"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Gang Li","raw_affiliation_strings":["Deakin University, Victoria, Australia","(Deakin University, Victoria, Australia)"],"affiliations":[{"raw_affiliation_string":"Deakin University, Victoria, Australia","institution_ids":["https://openalex.org/I149704539"]},{"raw_affiliation_string":"(Deakin University, Victoria, Australia)","institution_ids":["https://openalex.org/I149704539"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5070863501"],"corresponding_institution_ids":["https://openalex.org/I44468530"],"apc_list":null,"apc_paid":null,"fwci":1.858,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.87632147,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"393","last_page":"394"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9679999947547913,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9679999947547913,"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":0.9039000272750854,"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":0.8156816959381104},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.7585680484771729},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6985676884651184},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.6644663214683533},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5081555843353271},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4960416257381439},{"id":"https://openalex.org/keywords/partition","display_name":"Partition (number theory)","score":0.4843393564224243},{"id":"https://openalex.org/keywords/document-clustering","display_name":"Document clustering","score":0.48375630378723145},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4414653778076172},{"id":"https://openalex.org/keywords/subject","display_name":"Subject (documents)","score":0.42887893319129944},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.32178086042404175},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.11425140500068665},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07006409764289856}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8156816959381104},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.7585680484771729},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6985676884651184},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.6644663214683533},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5081555843353271},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4960416257381439},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.4843393564224243},{"id":"https://openalex.org/C177937566","wikidata":"https://www.wikidata.org/wiki/Q4223102","display_name":"Document clustering","level":3,"score":0.48375630378723145},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4414653778076172},{"id":"https://openalex.org/C2777855551","wikidata":"https://www.wikidata.org/wiki/Q12310021","display_name":"Subject (documents)","level":2,"score":0.42887893319129944},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.32178086042404175},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.11425140500068665},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07006409764289856},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"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/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/1816123.1816196","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1816123.1816196","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 10th annual joint conference on Digital libraries","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.vu.edu.au:32416","is_oa":false,"landing_page_url":"https://vuir.vu.edu.au/32416/","pdf_url":null,"source":{"id":"https://openalex.org/S4306400215","display_name":"Victoria University Research Repository (Victoria University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I41156924","host_organization_name":"Victoria University of Wellington","host_organization_lineage":["https://openalex.org/I41156924"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"PeerReviewed"},{"id":"pmh:oai:dro.deakin.edu.au:DU:30034432","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306402457","display_name":"Deakin Research Online (Deakin University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I149704539","host_organization_name":"Deakin University","host_organization_lineage":["https://openalex.org/I149704539"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Paper"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5799999833106995,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":1,"referenced_works":["https://openalex.org/W2088314245"],"related_works":["https://openalex.org/W17155033","https://openalex.org/W3207760230","https://openalex.org/W1496222301","https://openalex.org/W2019737068","https://openalex.org/W2899601636","https://openalex.org/W4254379378","https://openalex.org/W3015674157","https://openalex.org/W4206655101","https://openalex.org/W4237592971","https://openalex.org/W2387982377"],"abstract_inverted_index":{"\\n\\t\\t\\t\\t\\tImportant":[0],"words,":[1],"which":[2],"usually":[3,86],"exist":[4],"in":[5],"part":[6],"of":[7,18,34,66,82,128],"Title,":[8],"Subject":[9,63],"and":[10,36,64,68,88],"Keywords,":[11],"can":[12,114],"briefly":[13],"reflect":[14],"the":[15,31,78,89,106,120,126],"main":[16],"topic":[17,33],"a":[19,26,55,98],"document.":[20],"In":[21],"recent":[22],"years,":[23],"it":[24],"is":[25,96,101],"common":[27],"practice":[28],"to":[29,40,58,104],"exploit":[30],"semantic":[32],"documents":[35,71],"utilize":[37],"important":[38,60,75,83,94],"words":[39,61,84,95],"achieve":[41],"document":[42],"clustering,":[43],"especially":[44],"for":[45,93],"short":[46],"texts":[47],"such":[48],"as":[49],"news":[50],"articles.":[51],"This":[52],"paper":[53],"proposes":[54],"novel":[56],"method":[57,100],"extract":[59],"from":[62],"Keywords":[65],"articles,":[67],"then":[69,102],"partition":[70],"only":[72],"with":[73],"those":[74],"words.":[76],"Considering":[77],"fact":[79],"that":[80,110],"frequencies":[81],"are":[85],"low":[87],"scale":[90,107],"matrix":[91],"dataset":[92,108],"small,":[97],"normalization":[99],"proposed":[103],"normalize":[105],"so":[109],"more":[111],"accurate":[112],"results":[113],"be":[115],"achieved":[116],"by":[117],"sufficiently":[118],"exploiting":[119],"limited":[121],"information.":[122],"The":[123],"experiments":[124],"validate":[125],"effectiveness":[127],"our":[129],"method.<br":[130],"/>\\n\\t\\t\\t\\t":[131]},"counts_by_year":[{"year":2017,"cited_by_count":1},{"year":2014,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}