{"id":"https://openalex.org/W2023014905","doi":"https://doi.org/10.1109/cist.2012.6388065","title":"Stemming versus Light Stemming for measuring the simitilarity between Arabic Words with Latent Semantic Analysis model","display_name":"Stemming versus Light Stemming for measuring the simitilarity between Arabic Words with Latent Semantic Analysis model","publication_year":2012,"publication_date":"2012-10-01","ids":{"openalex":"https://openalex.org/W2023014905","doi":"https://doi.org/10.1109/cist.2012.6388065","mag":"2023014905"},"language":"en","primary_location":{"id":"doi:10.1109/cist.2012.6388065","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cist.2012.6388065","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 Colloquium in Information Science and Technology","raw_type":"proceedings-article"},"type":"conference-paper","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/A5008682196","display_name":"Hanane Froud","orcid":null},"institutions":[{"id":"https://openalex.org/I81605866","display_name":"Sidi Mohamed Ben Abdellah University","ror":"https://ror.org/04efg9a07","country_code":"MA","type":"education","lineage":["https://openalex.org/I81605866"]}],"countries":["MA"],"is_corresponding":false,"raw_author_name":"Hanane Froud","raw_affiliation_strings":["L. S.I. S, E.N. S.A, University Sidi Mohamed Ben Abdellah, Fez, Morocco","L.S.I.S, E.N.S.A, University Sidi Mohamed Ben Abdellah (USMBA), Fez, Morocco"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"L. S.I. S, E.N. S.A, University Sidi Mohamed Ben Abdellah, Fez, Morocco","institution_ids":["https://openalex.org/I81605866"]},{"raw_affiliation_string":"L.S.I.S, E.N.S.A, University Sidi Mohamed Ben Abdellah (USMBA), Fez, Morocco","institution_ids":["https://openalex.org/I81605866"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021071699","display_name":"Abdelmonaime Lachkar","orcid":null},"institutions":[{"id":"https://openalex.org/I81605866","display_name":"Sidi Mohamed Ben Abdellah University","ror":"https://ror.org/04efg9a07","country_code":"MA","type":"education","lineage":["https://openalex.org/I81605866"]}],"countries":["MA"],"is_corresponding":false,"raw_author_name":"Abdelmonaime Lachkar","raw_affiliation_strings":["L. S.I. S, E.N. S.A, University Sidi Mohamed Ben Abdellah, Fez, Morocco","L.S.I.S, E.N.S.A, University Sidi Mohamed Ben Abdellah (USMBA), Fez, Morocco"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"L. S.I. S, E.N. S.A, University Sidi Mohamed Ben Abdellah, Fez, Morocco","institution_ids":["https://openalex.org/I81605866"]},{"raw_affiliation_string":"L.S.I.S, E.N.S.A, University Sidi Mohamed Ben Abdellah (USMBA), Fez, Morocco","institution_ids":["https://openalex.org/I81605866"]}]},{"author_position":"last","author":{"id":null,"display_name":"Said Alaoui Ouatik","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Said Alaoui Ouatik","raw_affiliation_strings":["Faculty of Science Dhar EL Mahraz (FSDM), Fez, Morocco","L.I.S.Q, Faculty of Science Dhar EL Mahraz, (FSDM), Fez, Morocco"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Science Dhar EL Mahraz (FSDM), Fez, Morocco","institution_ids":[]},{"raw_affiliation_string":"L.I.S.Q, Faculty of Science Dhar EL Mahraz, (FSDM), Fez, Morocco","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7808,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.68941449,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"3","issue":null,"first_page":"69","last_page":"73"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9995999932289124,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9995999932289124,"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/T10028","display_name":"Topic Modeling","score":0.9991999864578247,"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":0.9976999759674072,"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/natural-language-processing","display_name":"Natural language processing","score":0.7531952857971191},{"id":"https://openalex.org/keywords/jaccard-index","display_name":"Jaccard index","score":0.7308080196380615},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7271119356155396},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6706901788711548},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"Semantic similarity","score":0.6206685304641724},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.6041236519813538},{"id":"https://openalex.org/keywords/latent-semantic-analysis","display_name":"Latent semantic analysis","score":0.5948640704154968},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5813935995101929},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.519742488861084},{"id":"https://openalex.org/keywords/arabic","display_name":"Arabic","score":0.4572370648384094},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.4224736988544464},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.340843141078949},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.2533881962299347},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.09249982237815857}],"concepts":[{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7531952857971191},{"id":"https://openalex.org/C203519979","wikidata":"https://www.wikidata.org/wiki/Q865360","display_name":"Jaccard index","level":3,"score":0.7308080196380615},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7271119356155396},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6706901788711548},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.6206685304641724},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.6041236519813538},{"id":"https://openalex.org/C170133592","wikidata":"https://www.wikidata.org/wiki/Q1806883","display_name":"Latent semantic analysis","level":2,"score":0.5948640704154968},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5813935995101929},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.519742488861084},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.4572370648384094},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.4224736988544464},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.340843141078949},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2533881962299347},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.09249982237815857},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cist.2012.6388065","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cist.2012.6388065","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 Colloquium in Information Science and Technology","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.41999998688697815,"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/W6180593","https://openalex.org/W100415715","https://openalex.org/W1660390307","https://openalex.org/W2012474866","https://openalex.org/W2040058125","https://openalex.org/W2059887434","https://openalex.org/W2070412788","https://openalex.org/W2139161410","https://openalex.org/W2171367662","https://openalex.org/W2325227998","https://openalex.org/W4252434862","https://openalex.org/W4285719527","https://openalex.org/W6600250607","https://openalex.org/W6604108467","https://openalex.org/W6653386564","https://openalex.org/W6680707895"],"related_works":["https://openalex.org/W4254879869","https://openalex.org/W3022576529","https://openalex.org/W786657898","https://openalex.org/W3152143533","https://openalex.org/W1997853560","https://openalex.org/W3016822073","https://openalex.org/W2626769217","https://openalex.org/W4385572821","https://openalex.org/W2367617289","https://openalex.org/W2321844481"],"abstract_inverted_index":{"Representation":[0],"of":[1,36,64,98,129],"semantic":[2,27,80],"information":[3],"contained":[4],"in":[5,53],"the":[6,18,26,33,62,79,85,106,114,124,127,130,137,140,144,150],"words":[7,30,48,83,151],"is":[8,20],"needed":[9],"for":[10,77],"any":[11],"Arabic":[12,70,82],"Text":[13],"Mining":[14],"applications.":[15],"More":[16],"precisely,":[17],"purpose":[19],"to":[21,44,69],"better":[22],"take":[23],"into":[24],"account":[25],"dependencies":[28],"between":[29,47,81],"expressed":[31],"by":[32],"co-occurrence":[34],"frequencies":[35],"these":[37],"words.":[38],"There":[39],"have":[40],"been":[41],"many":[42],"proposals":[43],"compute":[45],"similarities":[46],"based":[49],"on":[50,123,136],"their":[51],"distributions":[52],"contexts.":[54],"In":[55],"this":[56],"paper,":[57],"we":[58],"compare":[59],"and":[60,73,101,113],"contrast":[61],"effect":[63],"two":[65],"preprocessing":[66],"techniques":[67,76],"applied":[68],"corpus:":[71],"Stemming,":[72],"Light":[74,141],"Stemming":[75,142,145,148],"measuring":[78],"with":[84,94],"well":[86],"known":[87],"abstractive":[88],"model":[89],"-Latent":[90],"Semantic":[91],"Analysis":[92],"(LSA)-":[93],"a":[95],"wide":[96],"variety":[97,128],"distance":[99],"functions":[100],"similarity":[102],"measures,":[103],"such":[104],"as":[105],"Euclidean":[107],"Distance,":[108],"Cosine":[109],"Similarity,":[110],"Jaccard":[111],"Coefficient,":[112],"Pearson":[115],"Correlation":[116],"Coefficient.":[117],"The":[118],"obtained":[119],"results":[120],"show":[121],"that,":[122],"one":[125],"hand,":[126,139],"corpus":[131],"produces":[132],"more":[133],"accurate":[134],"results;":[135],"other":[138],"outperformed":[143],"approach":[146],"because":[147],"affects":[149],"meanings.":[152]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":2},{"year":2013,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}