{"id":"https://openalex.org/W2150791526","doi":"https://doi.org/10.1145/1099554.1099633","title":"Text document clustering based on frequent word sequences","display_name":"Text document clustering based on frequent word sequences","publication_year":2005,"publication_date":"2005-10-31","ids":{"openalex":"https://openalex.org/W2150791526","doi":"https://doi.org/10.1145/1099554.1099633","mag":"2150791526"},"language":"en","primary_location":{"id":"doi:10.1145/1099554.1099633","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1099554.1099633","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th 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/A5100382119","display_name":"Yanjun Li","orcid":"https://orcid.org/0000-0002-6277-4189"},"institutions":[{"id":"https://openalex.org/I19648265","display_name":"Wright State University","ror":"https://ror.org/04qk6pt94","country_code":"US","type":"education","lineage":["https://openalex.org/I19648265"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yanjun Li","raw_affiliation_strings":["Wright State University, Dayton, OH"],"affiliations":[{"raw_affiliation_string":"Wright State University, Dayton, OH","institution_ids":["https://openalex.org/I19648265"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103233608","display_name":"Soon M. Chung","orcid":"https://orcid.org/0000-0001-6033-5636"},"institutions":[{"id":"https://openalex.org/I19648265","display_name":"Wright State University","ror":"https://ror.org/04qk6pt94","country_code":"US","type":"education","lineage":["https://openalex.org/I19648265"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Soon M. Chung","raw_affiliation_strings":["Wright State University, Dayton, OH"],"affiliations":[{"raw_affiliation_string":"Wright State University, Dayton, OH","institution_ids":["https://openalex.org/I19648265"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100382119"],"corresponding_institution_ids":["https://openalex.org/I19648265"],"apc_list":null,"apc_paid":null,"fwci":8.8582,"has_fulltext":false,"cited_by_count":32,"citation_normalized_percentile":{"value":0.97400761,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"293","last_page":"294"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9945999979972839,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9945999979972839,"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/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9932000041007996,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9908000230789185,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7447177767753601},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6799088716506958},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6470946669578552},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6451956629753113},{"id":"https://openalex.org/keywords/document-clustering","display_name":"Document clustering","score":0.6368292570114136},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5629763007164001},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3596562147140503},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.19447091221809387}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7447177767753601},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6799088716506958},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6470946669578552},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6451956629753113},{"id":"https://openalex.org/C177937566","wikidata":"https://www.wikidata.org/wiki/Q4223102","display_name":"Document clustering","level":3,"score":0.6368292570114136},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5629763007164001},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3596562147140503},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.19447091221809387},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1099554.1099633","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1099554.1099633","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th ACM international conference on Information and knowledge management","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.699999988079071,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W1546703457","https://openalex.org/W1651093245","https://openalex.org/W2100958137","https://openalex.org/W2533248932"],"related_works":["https://openalex.org/W1795405792","https://openalex.org/W2019737068","https://openalex.org/W2899601636","https://openalex.org/W4254379378","https://openalex.org/W3015674157","https://openalex.org/W4206655101","https://openalex.org/W52853789","https://openalex.org/W2154173369","https://openalex.org/W4237592971","https://openalex.org/W2105363053"],"abstract_inverted_index":{"In":[0,38],"this":[1],"paper,":[2],"we":[3],"propose":[4],"a":[5],"new":[6],"text":[7,36,94,107],"clustering":[8],"algorithm,":[9],"named":[10],"Clustering":[11],"based":[12],"on":[13,77,103],"Frequent":[14],"Word":[15],"Sequences":[16],"(CFWS).":[17],"A":[18],"word":[19,64,79,84],"sequence":[20],"is":[21],"frequent":[22,83],"if":[23],"it":[24,52],"occurs":[25],"in":[26,34,66],"more":[27],"than":[28],"certain":[29],"percentage":[30],"of":[31,57,63,72,106],"the":[32,35,39,41,60,67,70,78,82,93,104,113],"documents":[33,54],"database.":[37,95],"past,":[40],"vector":[42],"space":[43],"model":[44],"was":[45],"commonly":[46],"used":[47],"for":[48],"information":[49,91],"retrieval,":[50],"but":[51],"treats":[53],"as":[55],"bags":[56],"words,":[58],"ignoring":[59],"sequential":[61],"pattern":[62],"occurrences":[65],"documents.":[68],"However,":[69],"meaning":[71],"natural":[73],"languages":[74],"strongly":[75],"depends":[76],"sequences,":[80],"and":[81,89,98,109],"sequences":[85],"can":[86],"provide":[87],"compact":[88],"valuable":[90],"about":[92],"Bisecting":[96],"k-means":[97],"FIHC":[99],"algorithms":[100],"are":[101,110],"evaluated":[102],"performance":[105],"clustering,":[108],"compared":[111],"with":[112],"proposed":[114],"CFWS":[115,122],"algorithm.":[116],"It":[117],"has":[118,123],"been":[119],"shown":[120],"that":[121],"much":[124],"better":[125],"performance.":[126]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}