{"id":"https://openalex.org/W2898797881","doi":"https://doi.org/10.13053/cys-22-3-3034","title":"Unsupervised Creation of Normalization Dictionaries for Micro-Blogs in Arabic, French and English","display_name":"Unsupervised Creation of Normalization Dictionaries for Micro-Blogs in Arabic, French and English","publication_year":2018,"publication_date":"2018-09-30","ids":{"openalex":"https://openalex.org/W2898797881","doi":"https://doi.org/10.13053/cys-22-3-3034","mag":"2898797881"},"language":"en","primary_location":{"id":"doi:10.13053/cys-22-3-3034","is_oa":false,"landing_page_url":"https://doi.org/10.13053/cys-22-3-3034","pdf_url":null,"source":{"id":"https://openalex.org/S61446325","display_name":"Computaci\u00f3n y Sistemas","issn_l":"1405-5546","issn":["1405-5546","2007-9737"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319599","host_organization_name":"National Polytechnic Institute","host_organization_lineage":["https://openalex.org/P4310319599"],"host_organization_lineage_names":["National Polytechnic Institute"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computaci\u00f3n y Sistemas","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hal.science/hal-01958675","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5009782240","display_name":"Amal Htait","orcid":"https://orcid.org/0000-0003-4647-9996"},"institutions":[{"id":"https://openalex.org/I4210114274","display_name":"Laboratoire d\u2019Informatique et Syst\u00e8mes","ror":"https://ror.org/0257sgk90","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I143002897","https://openalex.org/I21491767","https://openalex.org/I4210114274"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Amal Htait","raw_affiliation_strings":["LSIS - Laboratoire des Sciences de l'Information et des Syst\u00e8mes (Domaine Universitaire de Saint-J\u00e9r\u00f4me\r\nBatiment Polytech\r\nAvenue Escadrille Normandie-Niemen\r\n13397 MARSEILLE CEDEX 20 - France)"],"affiliations":[{"raw_affiliation_string":"LSIS - Laboratoire des Sciences de l'Information et des Syst\u00e8mes (Domaine Universitaire de Saint-J\u00e9r\u00f4me\r\nBatiment Polytech\r\nAvenue Escadrille Normandie-Niemen\r\n13397 MARSEILLE CEDEX 20 - France)","institution_ids":["https://openalex.org/I4210114274"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058109847","display_name":"S\u00e9bastien Fournier","orcid":"https://orcid.org/0000-0002-1611-0744"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"S\u00e9bastien Fournier","raw_affiliation_strings":["DIMAG - Data, Information & content MAnagement Group (France)"],"affiliations":[{"raw_affiliation_string":"DIMAG - Data, Information & content MAnagement Group (France)","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059940694","display_name":"Patrice Bellot","orcid":"https://orcid.org/0000-0001-8698-5055"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Patrice Bellot","raw_affiliation_strings":["DIMAG - Data, Information & content MAnagement Group (France)"],"affiliations":[{"raw_affiliation_string":"DIMAG - Data, Information & content MAnagement Group (France)","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5009782240"],"corresponding_institution_ids":["https://openalex.org/I4210114274"],"apc_list":null,"apc_paid":null,"fwci":0.3258,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.68246651,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"22","issue":"3","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9998999834060669,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9998999834060669,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9930999875068665,"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/normalization","display_name":"Normalization (sociology)","score":0.7497900724411011},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7474700212478638},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6727771759033203},{"id":"https://openalex.org/keywords/word-embedding","display_name":"Word embedding","score":0.6491334438323975},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.6463906764984131},{"id":"https://openalex.org/keywords/arabic","display_name":"Arabic","score":0.6378621459007263},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6086924076080322},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.5693076848983765},{"id":"https://openalex.org/keywords/english-language","display_name":"English language","score":0.4568517804145813},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4129725992679596},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.2945277690887451},{"id":"https://openalex.org/keywords/sociology","display_name":"Sociology","score":0.06755483150482178}],"concepts":[{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.7497900724411011},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7474700212478638},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6727771759033203},{"id":"https://openalex.org/C2777462759","wikidata":"https://www.wikidata.org/wiki/Q18395344","display_name":"Word embedding","level":3,"score":0.6491334438323975},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.6463906764984131},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.6378621459007263},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6086924076080322},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.5693076848983765},{"id":"https://openalex.org/C2987496018","wikidata":"https://www.wikidata.org/wiki/Q1860","display_name":"English language","level":2,"score":0.4568517804145813},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4129725992679596},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.2945277690887451},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.06755483150482178},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.13053/cys-22-3-3034","is_oa":false,"landing_page_url":"https://doi.org/10.13053/cys-22-3-3034","pdf_url":null,"source":{"id":"https://openalex.org/S61446325","display_name":"Computaci\u00f3n y Sistemas","issn_l":"1405-5546","issn":["1405-5546","2007-9737"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319599","host_organization_name":"National Polytechnic Institute","host_organization_lineage":["https://openalex.org/P4310319599"],"host_organization_lineage_names":["National Polytechnic Institute"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computaci\u00f3n y Sistemas","raw_type":"journal-article"},{"id":"pmh:oai:HAL:hal-01958675v1","is_oa":true,"landing_page_url":"https://hal.science/hal-01958675","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://www.cys.cic.ipn.mx/ojs/index.php/CyS/article/view/3034/2514","raw_type":"Journal articles"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-01958675v1","is_oa":true,"landing_page_url":"https://hal.science/hal-01958675","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://www.cys.cic.ipn.mx/ojs/index.php/CyS/article/view/3034/2514","raw_type":"Journal articles"},"sustainable_development_goals":[{"score":0.8500000238418579,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W46659105","https://openalex.org/W1614298861","https://openalex.org/W1995875735","https://openalex.org/W2057900969","https://openalex.org/W2133503566","https://openalex.org/W2146867136","https://openalex.org/W2163942301","https://openalex.org/W2250243742","https://openalex.org/W2251237590","https://openalex.org/W2295710275","https://openalex.org/W2621251601","https://openalex.org/W2751434455","https://openalex.org/W2761545835","https://openalex.org/W2898797881","https://openalex.org/W2950577311","https://openalex.org/W2963151059","https://openalex.org/W2993383518"],"related_works":["https://openalex.org/W2591697403","https://openalex.org/W2953716828","https://openalex.org/W2904857019","https://openalex.org/W2944728705","https://openalex.org/W3011538607","https://openalex.org/W2904022177","https://openalex.org/W4321441197","https://openalex.org/W2359348847","https://openalex.org/W4294432981","https://openalex.org/W4321276295"],"abstract_inverted_index":{"Text":[0],"normalisation":[1],"is":[2,33],"a":[3,61,73,191],"necessity":[4],"to":[5,66,206],"correctand":[6],"make":[7],"more":[8],"sense":[9],"of":[10,22,45,75,77,108,135,157,166,183],"the":[11,85,100,158,181],"micro-blogs":[12,70],"messages,":[13,197],"for":[14,39,69,111,118,126,168,172,177,195],"information":[15],"retrieval":[16],"purposes.":[17],"Unfortunately,":[18],"tools":[19],"and":[20,56,89,122,130,148,175],"resources":[21],"text":[23,40],"normalization":[24,41,133,188],"are":[25],"rarely":[26],"shared.":[27],"In":[28,59],"this":[29],"paper,":[30],"an":[31,161,185,199],"approach":[32],"presented":[34],"based":[35],"onan":[36],"unsupervised":[37],"method":[38],"using":[42,184],"distributed":[43],"representations":[44],"words,":[46],"known":[47],"also":[48,131],"as":[49,96],"\"word":[50],"embedding\",":[51],"applied":[52],"on":[53],"Arabic,":[54,87],"French":[55,88,127,146,178],"English":[57,119,153,169,186],"Languages.":[58],"addition,":[60],"tool":[62,92,159,194],"will":[63,93],"be":[64,94],"supplied":[65],"create":[67],"dictionaries":[68,134],"normalisation,":[71],"in":[72,84,139,145,152,163,200,202],"form":[74],"pairs":[76,138,144,151],"misspelled":[78],"word":[79,102],"with":[80,190],"its":[81],"standard-form":[82],"word,":[83],"languages:":[86],"English.":[90],"The":[91,155],"available":[95],"open":[97],"source":[98],"including":[99],"resources:":[101],"embedding\u2019s":[103],"models":[104],"(with":[105],"vocabulary":[106],"size":[107],"million":[109,116],"words":[110,117,125],"Arabic":[112,140,173],"language":[113,120,128,147,187],"model,":[114],"5":[115],"model":[121],"683":[123],"thousand":[124,137,143,150],"model),":[129],"three":[132],"10":[136],"language,":[141,170],"3":[142],"18":[149],"language.":[154],"evaluation":[156],"shows":[160],"average":[162],"Normalization":[164],"success":[165],"96%":[167],"89.5%":[171],"Language":[174],"85%":[176],"Language.":[179],"Also,":[180],"results":[182],"dictionary":[189],"sentiment":[192],"analysis":[193],"micro-blog\u2019s":[196],"show":[198],"crease":[201],"f-measure":[203],"from":[204],"58.15":[205],"59.56.":[207]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
