{"id":"https://openalex.org/W2608844143","doi":"https://doi.org/10.1109/icmcs.2016.7905587","title":"Measuring documents similarity in large corpus using MapReduce algorithm","display_name":"Measuring documents similarity in large corpus using MapReduce algorithm","publication_year":2016,"publication_date":"2016-09-01","ids":{"openalex":"https://openalex.org/W2608844143","doi":"https://doi.org/10.1109/icmcs.2016.7905587","mag":"2608844143"},"language":"en","primary_location":{"id":"doi:10.1109/icmcs.2016.7905587","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icmcs.2016.7905587","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 5th International Conference on Multimedia Computing and Systems (ICMCS)","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/A5086010906","display_name":"Marouane Birjali","orcid":"https://orcid.org/0000-0001-9792-6034"},"institutions":[{"id":"https://openalex.org/I4210125507","display_name":"Chouaib Doukkali University","ror":"https://ror.org/036kgyt43","country_code":"MA","type":"education","lineage":["https://openalex.org/I4210125507"]}],"countries":["MA"],"is_corresponding":false,"raw_author_name":"Marouane Birjali","raw_affiliation_strings":["Department of Computer Sciences, University of Chouaib Doukkali, Eljadida, Morocco"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Sciences, University of Chouaib Doukkali, Eljadida, Morocco","institution_ids":["https://openalex.org/I4210125507"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001300162","display_name":"Abderrahim Beni\u2010Hssane","orcid":"https://orcid.org/0000-0001-8040-1741"},"institutions":[{"id":"https://openalex.org/I4210125507","display_name":"Chouaib Doukkali University","ror":"https://ror.org/036kgyt43","country_code":"MA","type":"education","lineage":["https://openalex.org/I4210125507"]}],"countries":["MA"],"is_corresponding":false,"raw_author_name":"Abderrahim Beni-Hssane","raw_affiliation_strings":["Department of Computer Sciences, University of Chouaib Doukkali, Eljadida, Morocco"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Sciences, University of Chouaib Doukkali, Eljadida, Morocco","institution_ids":["https://openalex.org/I4210125507"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088964736","display_name":"Mohammed Erritali","orcid":"https://orcid.org/0000-0002-1672-8085"},"institutions":[{"id":"https://openalex.org/I4210119856","display_name":"Universit\u00e9 Sultan Moulay Slimane","ror":"https://ror.org/02m8tb249","country_code":"MA","type":"education","lineage":["https://openalex.org/I4210119856"]}],"countries":["MA"],"is_corresponding":false,"raw_author_name":"Mohammed Erritali","raw_affiliation_strings":["Department of Computer Sciences, University of Sultan Moulay Slimane, Beni Mellal, Morocco"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Sciences, University of Sultan Moulay Slimane, Beni Mellal, Morocco","institution_ids":["https://openalex.org/I4210119856"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8833,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.85843659,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"32","issue":null,"first_page":"24","last_page":"28"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9972000122070312,"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/T10028","display_name":"Topic Modeling","score":0.9972000122070312,"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":0.9954000115394592,"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/T11719","display_name":"Data Quality and Management","score":0.9941999912261963,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8441704511642456},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.8081157207489014},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6251357793807983},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5689709186553955},{"id":"https://openalex.org/keywords/document-clustering","display_name":"Document clustering","score":0.53070467710495},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.463058203458786},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.41222071647644043},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3480125963687897},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.07036381959915161}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8441704511642456},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.8081157207489014},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6251357793807983},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5689709186553955},{"id":"https://openalex.org/C177937566","wikidata":"https://www.wikidata.org/wiki/Q4223102","display_name":"Document clustering","level":3,"score":0.53070467710495},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.463058203458786},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.41222071647644043},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3480125963687897},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.07036381959915161},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icmcs.2016.7905587","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icmcs.2016.7905587","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 5th International Conference on Multimedia Computing and Systems (ICMCS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1494404649","https://openalex.org/W1647729745","https://openalex.org/W1977729554","https://openalex.org/W2010178645","https://openalex.org/W2082889357","https://openalex.org/W2087739686","https://openalex.org/W2100935296","https://openalex.org/W2136480620","https://openalex.org/W2154628803","https://openalex.org/W2274643260","https://openalex.org/W2544838495","https://openalex.org/W2950225692","https://openalex.org/W6629558247","https://openalex.org/W6636975626","https://openalex.org/W6675339850","https://openalex.org/W6677712588"],"related_works":["https://openalex.org/W4298130764","https://openalex.org/W2804364458","https://openalex.org/W42295635","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":{"Document":[0],"similarity":[1,16,46,76,88],"measures":[2],"between":[3,47,89],"documents":[4,18,61,90],"and":[5,31,135],"queries":[6],"has":[7],"been":[8],"extensively":[9],"studied":[10],"in":[11,62,91,129],"information":[12,27],"retrieval.":[13],"Measuring":[14],"the":[15,45,75,100,126,137,140],"of":[17,22,40,52,59,66,69,86,94,131,139],"are":[19,36,71],"crucial":[20],"components":[21],"many":[23],"text-analysis":[24],"tasks,":[25],"including":[26],"retrieval,":[28],"document":[29,32],"classification,":[30],"clustering.":[33],"However,":[34],"there":[35],"a":[37,56,63],"growing":[38],"number":[39,58],"tasks":[41],"that":[42,120],"require":[43],"computing":[44],"two":[48],"very":[49],"short":[50],"segments":[51],"text.":[53],"There":[54],"exist":[55],"large":[57,64,92],"composed":[60],"amount":[65,93],"corpus.":[67,95],"Most":[68],"them":[70],"required":[72],"to":[73],"compute":[74],"for":[77],"validation.":[78],"In":[79],"this":[80],"paper,":[81],"we":[82,98],"propose":[83],"our":[84,110,121],"approach":[85,102],"measuring":[87],"For":[96],"evaluation,":[97],"compare":[99],"proposed":[101],"with":[103],"other":[104],"approaches":[105],"previously":[106],"presented":[107],"by":[108],"using":[109],"new":[111,122],"MapReduce":[112,123],"algorithm.":[113],"Simulation":[114],"results,":[115],"on":[116],"Hadoop":[117],"framework,":[118],"show":[119],"algorithm":[124],"outperforms":[125],"classical":[127],"ones":[128],"term":[130],"running":[132],"time":[133],"performance":[134],"increases":[136],"value":[138],"similarity.":[141]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
