{"id":"https://openalex.org/W2911679991","doi":"https://doi.org/10.1142/s0218488519500041","title":"Finding Similar Documents Using Frequent Pattern Mining Methods","display_name":"Finding Similar Documents Using Frequent Pattern Mining Methods","publication_year":2019,"publication_date":"2019-01-31","ids":{"openalex":"https://openalex.org/W2911679991","doi":"https://doi.org/10.1142/s0218488519500041","mag":"2911679991"},"language":"en","primary_location":{"id":"doi:10.1142/s0218488519500041","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0218488519500041","pdf_url":null,"source":{"id":"https://openalex.org/S69518169","display_name":"International Journal of Uncertainty Fuzziness and Knowledge-Based Systems","issn_l":"0218-4885","issn":["0218-4885","1793-6411"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems","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/A5045821587","display_name":"Mohammad Karim Sohrabi","orcid":"https://orcid.org/0000-0001-8066-0356"},"institutions":[{"id":"https://openalex.org/I4210104301","display_name":"Islamic Azad University Semnan","ror":"https://ror.org/01abrxp85","country_code":"IR","type":"education","lineage":["https://openalex.org/I110525433","https://openalex.org/I4210104301"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Mohammad Karim Sohrabi","raw_affiliation_strings":["Department of Computer Engineering, Semnan Branch, Islamic Azad University, Semnan, Iran"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Engineering, Semnan Branch, Islamic Azad University, Semnan, Iran","institution_ids":["https://openalex.org/I4210104301"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057916757","display_name":"Hossein Azgomi","orcid":"https://orcid.org/0000-0001-7974-1845"},"institutions":[{"id":"https://openalex.org/I4210104301","display_name":"Islamic Azad University Semnan","ror":"https://ror.org/01abrxp85","country_code":"IR","type":"education","lineage":["https://openalex.org/I110525433","https://openalex.org/I4210104301"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Hossein Azgomi","raw_affiliation_strings":["Department of Computer Engineering, Semnan Branch, Islamic Azad University, Semnan, Iran"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Engineering, Semnan Branch, Islamic Azad University, Semnan, Iran","institution_ids":["https://openalex.org/I4210104301"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210104301"],"apc_list":null,"apc_paid":null,"fwci":1.3777,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.85531044,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":"27","issue":"01","first_page":"73","last_page":"96"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9994999766349792,"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":0.9994999766349792,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.994700014591217,"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":0.9864000082015991,"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/data-mining","display_name":"Data mining","score":0.7586311101913452},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7500045299530029},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.6729261875152588},{"id":"https://openalex.org/keywords/apriori-algorithm","display_name":"Apriori algorithm","score":0.6136566996574402},{"id":"https://openalex.org/keywords/a-priori-and-a-posteriori","display_name":"A priori and a posteriori","score":0.5823817849159241},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5472455024719238},{"id":"https://openalex.org/keywords/nearest-neighbor-search","display_name":"Nearest neighbor search","score":0.5130606889724731},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.4996767044067383},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.427756667137146},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3822641968727112},{"id":"https://openalex.org/keywords/association-rule-learning","display_name":"Association rule learning","score":0.33313024044036865},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2173808217048645},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.07596537470817566}],"concepts":[{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.7586311101913452},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7500045299530029},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6729261875152588},{"id":"https://openalex.org/C81440476","wikidata":"https://www.wikidata.org/wiki/Q513511","display_name":"Apriori algorithm","level":3,"score":0.6136566996574402},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.5823817849159241},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5472455024719238},{"id":"https://openalex.org/C116738811","wikidata":"https://www.wikidata.org/wiki/Q608751","display_name":"Nearest neighbor search","level":2,"score":0.5130606889724731},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.4996767044067383},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.427756667137146},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3822641968727112},{"id":"https://openalex.org/C193524817","wikidata":"https://www.wikidata.org/wiki/Q386780","display_name":"Association rule learning","level":2,"score":0.33313024044036865},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2173808217048645},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.07596537470817566},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1142/s0218488519500041","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0218488519500041","pdf_url":null,"source":{"id":"https://openalex.org/S69518169","display_name":"International Journal of Uncertainty Fuzziness and Knowledge-Based Systems","issn_l":"0218-4885","issn":["0218-4885","1793-6411"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1967587054","https://openalex.org/W1981838369","https://openalex.org/W1991711810","https://openalex.org/W2008840123","https://openalex.org/W2011853463","https://openalex.org/W2040929975","https://openalex.org/W2079191533","https://openalex.org/W2081193615","https://openalex.org/W2094963775","https://openalex.org/W2119931182","https://openalex.org/W2120387104","https://openalex.org/W2131752763","https://openalex.org/W2138614768","https://openalex.org/W2160595606","https://openalex.org/W2161687051","https://openalex.org/W2165139896","https://openalex.org/W2211041058","https://openalex.org/W2289945304","https://openalex.org/W2293071398","https://openalex.org/W2320617691","https://openalex.org/W2412717105","https://openalex.org/W2415270779","https://openalex.org/W2424774996","https://openalex.org/W2507917352","https://openalex.org/W2520737683","https://openalex.org/W2556688773","https://openalex.org/W2561008552","https://openalex.org/W2584741845","https://openalex.org/W2584857988","https://openalex.org/W2608731915","https://openalex.org/W2610617435","https://openalex.org/W2617990047","https://openalex.org/W2724365251","https://openalex.org/W2728576957","https://openalex.org/W2738417325","https://openalex.org/W2743513849","https://openalex.org/W2750037802","https://openalex.org/W2753144265","https://openalex.org/W2758461185","https://openalex.org/W4232177466"],"related_works":["https://openalex.org/W2059333989","https://openalex.org/W2385229093","https://openalex.org/W2367209111","https://openalex.org/W2390051172","https://openalex.org/W2118198359","https://openalex.org/W4299529113","https://openalex.org/W2348237075","https://openalex.org/W2340440656","https://openalex.org/W2355391054","https://openalex.org/W2382078898"],"abstract_inverted_index":{"Various":[0],"problems":[1],"are":[2,122],"just":[3],"rising":[4],"with":[5],"regard":[6],"to":[7,26,37,53,133],"mining":[8,81,107],"in":[9,148],"massive":[10],"datasets,":[11],"among":[12],"which":[13,131],"finding":[14,74,165],"similar":[15,75,146,166],"documents":[16,76,147],"can":[17],"be":[18],"pinpointed.":[19],"The":[20,142],"Shingling":[21],"method":[22,46,52,70,144,154,157],"converts":[23],"this":[24,66,84],"problem":[25,102],"a":[27,104,110],"set-based":[28],"problem.":[29,97],"Some":[30],"of":[31,63,113,127,175,178],"existing":[32],"methods":[33],"have":[34,49],"used":[35],"min-hashing":[36],"compress":[38],"the":[39,44,86,99,118,123,128,152,172,176,179],"results":[40,170],"already":[41],"driven":[42],"from":[43,60],"shingling":[45],"and":[47,91,115,138,155],"then":[48],"exploited":[50],"LSH":[51],"find":[54],"candidate":[55,162],"pairs":[56,62,163],"for":[57,73,94,164],"similarity":[58,95,100],"search":[59,96,101],"all":[61],"documents.":[64,167],"In":[65],"paper,":[67],"an":[68],"apriori-based":[69],"is":[71,89,92],"proposed":[72,129,143,180],"based":[77],"on":[78],"frequent":[79,105],"itemset":[80],"approach.":[82],"To":[83],"end,":[85],"apriori":[87],"algorithm":[88],"modified":[90,111],"customized":[93],"Modeling":[98],"as":[103],"pattern":[106],"problem,":[108],"using":[109],"version":[112],"apriori,":[114],"dynamic":[116],"selection":[117],"minimum":[119],"support":[120],"threshold":[121],"most":[124],"important":[125],"advantages":[126],"method,":[130],"lead":[132],"its":[134],"appropriate":[135],"execution":[136],"time":[137,150],"high":[139,173],"quality":[140,174],"results.":[141],"finds":[145],"less":[149],"than":[151],"combined":[153],"MCVM":[156],"because":[158],"it":[159],"generates":[160],"fewer":[161],"Furthermore,":[168],"experimental":[169],"show":[171],"answers":[177],"methods.":[181]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2019,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}