{"id":"https://openalex.org/W1493497007","doi":"https://doi.org/10.1109/rcis.2015.7128906","title":"Arabic document similarity analysis using n-grams and singular value decomposition","display_name":"Arabic document similarity analysis using n-grams and singular value decomposition","publication_year":2015,"publication_date":"2015-05-01","ids":{"openalex":"https://openalex.org/W1493497007","doi":"https://doi.org/10.1109/rcis.2015.7128906","mag":"1493497007"},"language":"en","primary_location":{"id":"doi:10.1109/rcis.2015.7128906","is_oa":false,"landing_page_url":"https://doi.org/10.1109/rcis.2015.7128906","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE 9th International Conference on Research Challenges in Information Science (RCIS)","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/A5068758385","display_name":"Ashraf S. Hussein","orcid":"https://orcid.org/0000-0002-5222-0799"},"institutions":[{"id":"https://openalex.org/I4210093932","display_name":"Arab Open University","ror":"https://ror.org/00fp9k450","country_code":"KW","type":"education","lineage":["https://openalex.org/I4210093932"]},{"id":"https://openalex.org/I124391630","display_name":"Arab Open University","ror":"https://ror.org/04dqhen73","country_code":"OM","type":"education","lineage":["https://openalex.org/I124391630","https://openalex.org/I4210093932"]}],"countries":["KW","OM"],"is_corresponding":true,"raw_author_name":"Ashraf S. Hussein","raw_affiliation_strings":["Faculty of Information Technology and Computing, Arab Open University, Headquarters Kuwait","Faculty of Information Technology and Computing, Arab Open University, Headquarters, Kuwait"],"affiliations":[{"raw_affiliation_string":"Faculty of Information Technology and Computing, Arab Open University, Headquarters Kuwait","institution_ids":["https://openalex.org/I4210093932","https://openalex.org/I124391630"]},{"raw_affiliation_string":"Faculty of Information Technology and Computing, Arab Open University, Headquarters, Kuwait","institution_ids":["https://openalex.org/I124391630"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5068758385"],"corresponding_institution_ids":["https://openalex.org/I124391630","https://openalex.org/I4210093932"],"apc_list":null,"apc_paid":null,"fwci":5.1773,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.95466723,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"445","last_page":"455"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9980000257492065,"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":0.9980000257492065,"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/T11492","display_name":"Academic integrity and plagiarism","score":0.9968000054359436,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12380","display_name":"Authorship Attribution and Profiling","score":0.9965999722480774,"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/computer-science","display_name":"Computer science","score":0.8089861273765564},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6863458156585693},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6481223106384277},{"id":"https://openalex.org/keywords/lexical-analysis","display_name":"Lexical analysis","score":0.6082811951637268},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.577420175075531},{"id":"https://openalex.org/keywords/tf\u2013idf","display_name":"tf\u2013idf","score":0.4595358371734619},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.1697605848312378},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.09984102845191956}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8089861273765564},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6863458156585693},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6481223106384277},{"id":"https://openalex.org/C176982825","wikidata":"https://www.wikidata.org/wiki/Q835922","display_name":"Lexical analysis","level":2,"score":0.6082811951637268},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.577420175075531},{"id":"https://openalex.org/C81758059","wikidata":"https://www.wikidata.org/wiki/Q796584","display_name":"tf\u2013idf","level":3,"score":0.4595358371734619},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.1697605848312378},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.09984102845191956},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/rcis.2015.7128906","is_oa":false,"landing_page_url":"https://doi.org/10.1109/rcis.2015.7128906","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE 9th International Conference on Research Challenges in Information Science (RCIS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.800000011920929}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W62386174","https://openalex.org/W87733252","https://openalex.org/W198154512","https://openalex.org/W583499102","https://openalex.org/W938539187","https://openalex.org/W1484792045","https://openalex.org/W1496503889","https://openalex.org/W1562017034","https://openalex.org/W1978394996","https://openalex.org/W1978433898","https://openalex.org/W1990061958","https://openalex.org/W2000921048","https://openalex.org/W2051966565","https://openalex.org/W2061263584","https://openalex.org/W2063231647","https://openalex.org/W2096194908","https://openalex.org/W2096753332","https://openalex.org/W2111295912","https://openalex.org/W2134141008","https://openalex.org/W2147742901","https://openalex.org/W2150409536","https://openalex.org/W2154822030","https://openalex.org/W2184952243","https://openalex.org/W2290464795","https://openalex.org/W2404948255","https://openalex.org/W2766514029","https://openalex.org/W4233484125","https://openalex.org/W4285719527","https://openalex.org/W6602575097","https://openalex.org/W6603554506","https://openalex.org/W6617045750","https://openalex.org/W6629600108","https://openalex.org/W6633670873","https://openalex.org/W6686208030","https://openalex.org/W6696693107","https://openalex.org/W6713305020"],"related_works":["https://openalex.org/W3107474891","https://openalex.org/W1690232763","https://openalex.org/W2038246283","https://openalex.org/W2349925400","https://openalex.org/W2889764925","https://openalex.org/W4281690070","https://openalex.org/W2063326701","https://openalex.org/W3187216840","https://openalex.org/W2149891536","https://openalex.org/W2006750207"],"abstract_inverted_index":{"The":[0,88,150,204],"computerized":[1],"methods":[2,49],"for":[3,69,250],"document":[4,70,190],"similarity":[5,71,193,253],"estimation":[6],"(or":[7],"plagiarism":[8],"detection)":[9],"in":[10,24,77,84,221],"natural":[11],"languages,":[12],"evolved":[13],"during":[14],"the":[15,36,45,81,95,108,131,169,173,188,198,207,231,234,244,251],"last":[16],"two":[17],"decades,":[18],"have":[19],"focused":[20],"on":[21,93,130,146],"English":[22],"language":[23,76],"particular":[25],"and":[26,33,56,99,115,136,165,177,192,224,243],"some":[27,225],"other":[28,37],"languages":[29,58],"such":[30,59,85],"as":[31,60],"German":[32],"Chinese.":[34],"On":[35],"hand,":[38],"there":[39],"are":[40,105,139,180,195],"several":[41],"language-independent":[42],"methods,":[43],"but":[44],"accuracy":[46],"of":[47,206,227,233,241],"these":[48],"is":[50,91,122,155],"not":[51],"satisfactory,":[52],"especially":[53,249],"with":[54,214,255],"morphological":[55,120,148],"complicated":[57],"Arabic.":[61],"This":[62],"paper":[63],"proposes":[64],"an":[65],"innovative":[66],"content-based":[67],"method":[68,90,144,209,236,246],"analysis":[72,114],"devoted":[73],"to":[74,79,239],"Arabic":[75,112],"order":[78],"bridge":[80],"existing":[82],"gap":[83],"software":[86],"solutions.":[87],"proposed":[89,208,235,245],"based":[92,145,159],"modeling":[94],"relation":[96],"between":[97,172],"documents":[98,179],"their":[100,178],"n-gram":[101,175],"phrases.":[102],"These":[103],"phrases":[104,176],"generated":[106],"from":[107,197],"normalized":[109],"text,":[110],"exploiting":[111],"morphology":[113],"lexical":[116,164],"lookup.":[117],"Resolving":[118],"possible":[119],"ambiguity":[121],"carried":[123],"out":[124],"through":[125,212],"applying":[126],"Part-of-Speech":[127],"(PoS)":[128],"tagging":[129],"examined":[132,151],"documents.":[133],"Text":[134],"indexing":[135],"stop-words":[137],"removal":[138],"performed,":[140],"employing":[141],"a":[142],"new":[143],"text":[147],"analysis.":[149],"documents'":[152],"TF-IDF":[153],"model":[154],"constructed":[156],"using":[157,182],"Heuristic":[158],"pair-wise":[160],"matching":[161],"algorithm,":[162],"considering":[163],"syntactic":[166,256],"changes.":[167,257],"Then,":[168],"hidden":[170],"associations":[171],"unique":[174],"investigated":[181],"Latent":[183],"Semantic":[184],"Analysis":[185],"(LSA).":[186],"Next,":[187],"pairwise":[189],"subset":[191],"measures":[194],"derived":[196],"Singular":[199],"Value":[200],"Decomposition":[201],"(SVD)":[202],"computations.":[203],"performance":[205],"was":[210,237],"confirmed":[211],"experiments":[213],"various":[215],"data":[216],"sets,":[217],"exhibiting":[218],"promising":[219],"capabilities":[220],"estimating":[222],"literal":[223],"types":[226],"intelligent":[228,252],"similarities.":[229],"Finally,":[230],"results":[232],"compared":[238],"that":[240],"Plagiarism-Checker-X,":[242,248],"outperformed":[247],"cases":[254]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":7},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1}],"updated_date":"2026-01-13T01:12:25.745995","created_date":"2025-10-10T00:00:00"}