{"id":"https://openalex.org/W3198053264","doi":"https://doi.org/10.1145/3460569.3460590","title":"Locality Sensitive Hashing Based Clustering for Large Scale Documents","display_name":"Locality Sensitive Hashing Based Clustering for Large Scale Documents","publication_year":2021,"publication_date":"2021-03-19","ids":{"openalex":"https://openalex.org/W3198053264","doi":"https://doi.org/10.1145/3460569.3460590","mag":"3198053264"},"language":"en","primary_location":{"id":"doi:10.1145/3460569.3460590","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3460569.3460590","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 6th International Conference on Mathematics and Artificial Intelligence","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/A5076910132","display_name":"Kevser \u00d6zdem Karaca","orcid":"https://orcid.org/0000-0002-6695-200X"},"institutions":[{"id":"https://openalex.org/I95634034","display_name":"Gazi University","ror":"https://ror.org/054xkpr46","country_code":"TR","type":"education","lineage":["https://openalex.org/I95634034"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Kevser \u00d6zdem","raw_affiliation_strings":["Gazi University, Turkey"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Gazi University, Turkey","institution_ids":["https://openalex.org/I95634034"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089059522","display_name":"M. Ali Ak\u00e7ayol","orcid":"https://orcid.org/0000-0002-6615-1237"},"institutions":[{"id":"https://openalex.org/I95634034","display_name":"Gazi University","ror":"https://ror.org/054xkpr46","country_code":"TR","type":"education","lineage":["https://openalex.org/I95634034"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"M. Ali Akcayol","raw_affiliation_strings":["Gazi University, Turkey"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Gazi University, Turkey","institution_ids":["https://openalex.org/I95634034"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1399,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.56110816,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"4","issue":null,"first_page":"137","last_page":"142"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9983000159263611,"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":0.9983000159263611,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9976000189781189,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9882000088691711,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/cluster-analysis","display_name":"Cluster analysis","score":0.8194075226783752},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7074072360992432},{"id":"https://openalex.org/keywords/silhouette","display_name":"Silhouette","score":0.6403016448020935},{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.6323801279067993},{"id":"https://openalex.org/keywords/locality-sensitive-hashing","display_name":"Locality-sensitive hashing","score":0.6171866059303284},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.6033264398574829},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5352367162704468},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.49881768226623535},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4892432689666748},{"id":"https://openalex.org/keywords/cluster","display_name":"Cluster (spacecraft)","score":0.4862593412399292},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4114364683628082},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3503870964050293},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3151344656944275},{"id":"https://openalex.org/keywords/hash-table","display_name":"Hash table","score":0.3015711009502411},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.09687793254852295},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.07785394787788391},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06566986441612244},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.06408736109733582}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.8194075226783752},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7074072360992432},{"id":"https://openalex.org/C58103923","wikidata":"https://www.wikidata.org/wiki/Q2286025","display_name":"Silhouette","level":2,"score":0.6403016448020935},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.6323801279067993},{"id":"https://openalex.org/C74270461","wikidata":"https://www.wikidata.org/wiki/Q1625299","display_name":"Locality-sensitive hashing","level":4,"score":0.6171866059303284},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.6033264398574829},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5352367162704468},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.49881768226623535},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4892432689666748},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.4862593412399292},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4114364683628082},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3503870964050293},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3151344656944275},{"id":"https://openalex.org/C67388219","wikidata":"https://www.wikidata.org/wiki/Q207440","display_name":"Hash table","level":3,"score":0.3015711009502411},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.09687793254852295},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.07785394787788391},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06566986441612244},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.06408736109733582},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3460569.3460590","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3460569.3460590","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 6th International Conference on Mathematics and Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6600000262260437,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1128809682","https://openalex.org/W1985059878","https://openalex.org/W2016464611","https://openalex.org/W2022760473","https://openalex.org/W2163261168","https://openalex.org/W2167971078","https://openalex.org/W2316340232","https://openalex.org/W2518417797","https://openalex.org/W2536903306","https://openalex.org/W2557865862","https://openalex.org/W2809140741","https://openalex.org/W2894942594","https://openalex.org/W2943264652"],"related_works":["https://openalex.org/W2000601968","https://openalex.org/W2135779989","https://openalex.org/W1835589799","https://openalex.org/W2144265691","https://openalex.org/W2033383639","https://openalex.org/W2754607325","https://openalex.org/W3108918257","https://openalex.org/W144856782","https://openalex.org/W2080135560","https://openalex.org/W3016124764"],"abstract_inverted_index":{"Nowadays,":[0],"the":[1,64,92],"size":[2,56],"of":[3,35,49,57],"data":[4],"continues":[5],"to":[6,28,31,76,91],"increase":[7],"more":[8],"rapidly":[9],"day":[10],"by":[11],"day.":[12],"Considering":[13],"this":[14,44],"situation,":[15],"large-scale":[16],"processing":[17],"has":[18,60],"become":[19],"a":[20,46,54],"very":[21],"important":[22],"issue":[23],"in":[24],"document":[25],"clustering,":[26],"due":[27],"its":[29],"capability":[30],"organize":[32],"large":[33],"numbers":[34],"documents":[36],"as":[37],"few":[38],"meaningful":[39],"and":[40,70,102,106],"consistent":[41],"clusters.":[42],"In":[43],"study,":[45],"dataset":[47],"consisting":[48],"390":[50],"English":[51],"textbooks":[52],"with":[53,79,100],"total":[55],"7.61":[58],"GB,":[59],"been":[61,74,84,98],"used":[62,75],"for":[63,104],"clustering":[65],"task.":[66],"Locality":[67],"sensitive":[68],"hashing":[69],"k-shingles":[71],"methods":[72],"have":[73,83,97],"obtain":[77],"clusters":[78,96],"high":[80],"quality.":[81],"Clusters":[82],"evaluated":[85],"using":[86],"cluster":[87],"validity":[88],"indices.":[89],"According":[90],"experimental":[93],"results,":[94],"high-quality":[95],"obtained,":[99],"0.88":[101],"0.79":[103],"Silhouette":[105],"Davies\u2013Bouldin":[107],"scores,":[108],"respectively.":[109]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
