{"id":"https://openalex.org/W2012008289","doi":"https://doi.org/10.4304/jcp.6.10.2180-2186","title":"Text Clustering Using a Suffix Tree Similarity Measure","display_name":"Text Clustering Using a Suffix Tree Similarity Measure","publication_year":2011,"publication_date":"2011-09-27","ids":{"openalex":"https://openalex.org/W2012008289","doi":"https://doi.org/10.4304/jcp.6.10.2180-2186","mag":"2012008289"},"language":"en","primary_location":{"id":"doi:10.4304/jcp.6.10.2180-2186","is_oa":false,"landing_page_url":"https://doi.org/10.4304/jcp.6.10.2180-2186","pdf_url":null,"source":{"id":"https://openalex.org/S77894049","display_name":"Journal of Computers","issn_l":"1796-203X","issn":["1796-203X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318660","host_organization_name":"Academy Publisher","host_organization_lineage":["https://openalex.org/P4310318660"],"host_organization_lineage_names":["Academy Publisher"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Computers","raw_type":"journal-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/A5087130250","display_name":"Chenghui Huang","orcid":"https://orcid.org/0009-0001-2578-6607"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Chenghui HUANG","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017205177","display_name":"Jian Yin","orcid":"https://orcid.org/0000-0002-1214-5384"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jian YIN","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5035012892","display_name":"Fang Hou","orcid":"https://orcid.org/0000-0003-4811-5918"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fang HOU","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5087130250"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.7103,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.86177886,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"6","issue":"10","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9970999956130981,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9970999956130981,"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":0.9970999956130981,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9961000084877014,"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/suffix","display_name":"Suffix","score":0.6725174188613892},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6133381128311157},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.6038476228713989},{"id":"https://openalex.org/keywords/suffix-tree","display_name":"Suffix tree","score":0.5947123765945435},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.589177668094635},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5771609544754028},{"id":"https://openalex.org/keywords/similarity-measure","display_name":"Similarity measure","score":0.5166614055633545},{"id":"https://openalex.org/keywords/generalized-suffix-tree","display_name":"Generalized suffix tree","score":0.49341192841529846},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.45717909932136536},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44722428917884827},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.38143646717071533},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3256416320800781},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.2851036489009857},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.21705684065818787},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.055091679096221924}],"concepts":[{"id":"https://openalex.org/C2779804580","wikidata":"https://www.wikidata.org/wiki/Q102047","display_name":"Suffix","level":2,"score":0.6725174188613892},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6133381128311157},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.6038476228713989},{"id":"https://openalex.org/C2781166958","wikidata":"https://www.wikidata.org/wiki/Q1426863","display_name":"Suffix tree","level":3,"score":0.5947123765945435},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.589177668094635},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5771609544754028},{"id":"https://openalex.org/C2776517306","wikidata":"https://www.wikidata.org/wiki/Q29017317","display_name":"Similarity measure","level":2,"score":0.5166614055633545},{"id":"https://openalex.org/C118146561","wikidata":"https://www.wikidata.org/wiki/Q5532514","display_name":"Generalized suffix tree","level":4,"score":0.49341192841529846},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.45717909932136536},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44722428917884827},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.38143646717071533},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3256416320800781},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2851036489009857},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.21705684065818787},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.055091679096221924},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.4304/jcp.6.10.2180-2186","is_oa":false,"landing_page_url":"https://doi.org/10.4304/jcp.6.10.2180-2186","pdf_url":null,"source":{"id":"https://openalex.org/S77894049","display_name":"Journal of Computers","issn_l":"1796-203X","issn":["1796-203X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318660","host_organization_name":"Academy Publisher","host_organization_lineage":["https://openalex.org/P4310318660"],"host_organization_lineage_names":["Academy Publisher"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Computers","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5400000214576721,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W113396932","https://openalex.org/W1500125366","https://openalex.org/W1521439890","https://openalex.org/W1746620543","https://openalex.org/W1971785050","https://openalex.org/W2000918452","https://openalex.org/W2000982728","https://openalex.org/W2081980673","https://openalex.org/W2082171025","https://openalex.org/W2089391273","https://openalex.org/W2100958137","https://openalex.org/W2109803107","https://openalex.org/W2147152072","https://openalex.org/W2153390303","https://openalex.org/W2165612380","https://openalex.org/W6631328736","https://openalex.org/W6672968584"],"related_works":["https://openalex.org/W96331545","https://openalex.org/W1517600056","https://openalex.org/W1575722140","https://openalex.org/W2036633468","https://openalex.org/W2160738675","https://openalex.org/W1548907175","https://openalex.org/W2003608043","https://openalex.org/W4293529780","https://openalex.org/W3022556214","https://openalex.org/W2405892617"],"abstract_inverted_index":{"In":[0],"text":[1,47,62,92],"mining":[2],"area,":[3],"popular":[4],"methods":[5,18],"use":[6],"the":[7,20,25,51,58,61,90,99,102,120],"bag-of-words":[8],"models,":[9],"which":[10],"represent":[11],"a":[12,15,37,68],"document":[13,82],"as":[14],"vector.":[16],"These":[17],"ignored":[19],"word":[21,52,106],"sequence":[22,53,107],"information,":[23,54],"and":[24,55,86],"good":[26],"clustering":[27],"result":[28],"limited":[29],"to":[30],"some":[31],"special":[32],"domains.":[33],"This":[34],"paper":[35],"proposes":[36],"new":[38,91],"similarity":[39,59,71,93],"measure":[40,94],"based":[41,108],"on":[42,80,119],"suffix":[43,69],"tree":[44,70],"model":[45],"of":[46,64,101,116,122],"documents.":[48],"It":[49],"analyzes":[50],"then":[56],"computes":[57],"between":[60],"documents":[63],"corpus":[65,84],"by":[66],"applying":[67],"that":[72,89],"combines":[73],"with":[74,98],"TF-IDF":[75],"weighting":[76],"method.":[77],"Experimental":[78],"results":[79,100],"standard":[81],"benchmark":[83],"RUTERS":[85],"BBC":[87],"indicate":[88],"is":[95],"effective.":[96],"Comparing":[97],"other":[103],"two":[104],"frequent":[105],"methods,":[109],"our":[110],"proposed":[111],"method":[112],"achieves":[113],"an":[114],"improvement":[115],"about":[117],"15%":[118],"average":[121],"F-Measure":[123],"score.":[124]},"counts_by_year":[{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}