{"id":"https://openalex.org/W2202210819","doi":"https://doi.org/10.1145/2665077","title":"Keyword Extraction from Arabic Documents using Term Equivalence Classes","display_name":"Keyword Extraction from Arabic Documents using Term Equivalence Classes","publication_year":2015,"publication_date":"2015-04-20","ids":{"openalex":"https://openalex.org/W2202210819","doi":"https://doi.org/10.1145/2665077","mag":"2202210819"},"language":"en","primary_location":{"id":"doi:10.1145/2665077","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2665077","pdf_url":null,"source":{"id":"https://openalex.org/S4306421405","display_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","issn_l":"2375-4699","issn":["2375-4699","2375-4702"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","raw_type":"journal-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/A5062695565","display_name":"Arafat Awajan","orcid":"https://orcid.org/0000-0002-7067-5658"},"institutions":[{"id":"https://openalex.org/I158749337","display_name":"Princess Sumaya University for Technology","ror":"https://ror.org/01jy46q10","country_code":"JO","type":"education","lineage":["https://openalex.org/I158749337"]}],"countries":["JO"],"is_corresponding":true,"raw_author_name":"Arafat Awajan","raw_affiliation_strings":["Princess Sumaya University for Technology, Jordan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Princess Sumaya University for Technology, Jordan","institution_ids":["https://openalex.org/I158749337"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5062695565"],"corresponding_institution_ids":["https://openalex.org/I158749337"],"apc_list":null,"apc_paid":null,"fwci":2.2259,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.90642643,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"14","issue":"2","first_page":"1","last_page":"18"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis 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/T13083","display_name":"Advanced Text Analysis 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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9024999737739563,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.7415274381637573},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.6055184006690979},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.600034773349762},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.5798038244247437},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5703598260879517},{"id":"https://openalex.org/keywords/equivalence","display_name":"Equivalence (formal languages)","score":0.5496278405189514},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4968893826007843},{"id":"https://openalex.org/keywords/vector-space-model","display_name":"Vector space model","score":0.4946763217449188},{"id":"https://openalex.org/keywords/arabic","display_name":"Arabic","score":0.4908366799354553},{"id":"https://openalex.org/keywords/automatic-indexing","display_name":"Automatic indexing","score":0.48858579993247986},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.205072283744812},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.15303349494934082}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7415274381637573},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.6055184006690979},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.600034773349762},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.5798038244247437},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5703598260879517},{"id":"https://openalex.org/C2780069185","wikidata":"https://www.wikidata.org/wiki/Q7977945","display_name":"Equivalence (formal languages)","level":2,"score":0.5496278405189514},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4968893826007843},{"id":"https://openalex.org/C89686163","wikidata":"https://www.wikidata.org/wiki/Q1187982","display_name":"Vector space model","level":2,"score":0.4946763217449188},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.4908366799354553},{"id":"https://openalex.org/C2778330532","wikidata":"https://www.wikidata.org/wiki/Q4826577","display_name":"Automatic indexing","level":3,"score":0.48858579993247986},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.205072283744812},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.15303349494934082},{"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},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2665077","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2665077","pdf_url":null,"source":{"id":"https://openalex.org/S4306421405","display_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","issn_l":"2375-4699","issn":["2375-4699","2375-4702"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8299999833106995,"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":24,"referenced_works":["https://openalex.org/W7155555","https://openalex.org/W142212369","https://openalex.org/W144571221","https://openalex.org/W201141796","https://openalex.org/W1532325895","https://openalex.org/W1537816770","https://openalex.org/W1596451018","https://openalex.org/W1970482722","https://openalex.org/W2009466421","https://openalex.org/W2045181608","https://openalex.org/W2060772621","https://openalex.org/W2061118645","https://openalex.org/W2062233052","https://openalex.org/W2064418625","https://openalex.org/W2133286915","https://openalex.org/W2134141008","https://openalex.org/W2144211451","https://openalex.org/W2149709850","https://openalex.org/W2158018156","https://openalex.org/W2165612380","https://openalex.org/W2294764339","https://openalex.org/W2593831809","https://openalex.org/W2892737606","https://openalex.org/W6600280465"],"related_works":["https://openalex.org/W204619012","https://openalex.org/W2398073981","https://openalex.org/W2165612380","https://openalex.org/W4247874641","https://openalex.org/W2008087111","https://openalex.org/W2051392313","https://openalex.org/W2081057833","https://openalex.org/W2025451713","https://openalex.org/W2062327384","https://openalex.org/W2168066506"],"abstract_inverted_index":{"The":[0,101,135],"rapid":[1],"growth":[2],"of":[3,18,22,35,85,118,206,211],"the":[4,16,30,77,86,107,113,129,133,146,151,155,160,180,185,196],"Internet":[5],"and":[6,33,44,82,115,154,166,208],"other":[7],"computing":[8],"facilities":[9],"in":[10,15,24,32,144,184],"recent":[11],"years":[12],"has":[13,28],"resulted":[14],"creation":[17],"a":[19,66,191],"large":[20],"amount":[21],"text":[23,38,87,102],"electronic":[25],"form,":[26],"which":[27,145],"increased":[29],"interest":[31],"importance":[34],"different":[36],"automatic":[37],"processing":[39],"applications,":[40,54],"including":[41],"keyword":[42],"extraction":[43],"term":[45],"indexing.":[46],"Although":[47],"keywords":[48,70,78],"are":[49,59,139,163],"very":[50],"useful":[51],"for":[52,68],"many":[53],"most":[55,136,181],"documents":[56],"available":[57],"online":[58],"not":[60],"provided":[61],"with":[62,202],"keywords.":[63,218],"We":[64],"describe":[65],"method":[67,75,198],"extracting":[69],"from":[71,92,97,132,150,159],"Arabic":[72],"documents.":[73],"This":[74],"identifies":[76],"by":[79],"combining":[80],"linguistics":[81],"statistical":[83],"analysis":[84],"without":[88],"using":[89,190],"prior":[90],"knowledge":[91],"its":[93],"domain":[94],"or":[95],"information":[96],"any":[98],"related":[99],"corpus.":[100],"is":[103,124,169,175],"preprocessed":[104],"to":[105,127,178],"extract":[106],"main":[108],"linguistic":[109],"information,":[110],"such":[111],"as":[112],"roots":[114],"morphological":[116],"patterns":[117],"derivative":[119,147],"words.":[120],"A":[121,171],"cleaning":[122],"phase":[123],"then":[125,176],"applied":[126],"eliminate":[128],"meaningless":[130],"words":[131,148,157],"text.":[134,186],"frequent":[137,182],"terms":[138],"clustered":[140],"into":[141],"equivalence":[142],"classes":[143],"generated":[149,158],"same":[152,161],"root":[153],"non-derivative":[156],"stem":[162],"placed":[164],"together,":[165],"their":[167],"count":[168],"accumulated.":[170],"vector":[172],"space":[173],"model":[174],"used":[177],"capture":[179],"N-gram":[183],"Experiments":[187],"carried":[188],"out":[189],"real-world":[192],"dataset":[193],"show":[194],"that":[195],"proposed":[197],"achieves":[199],"good":[200],"results":[201],"an":[203],"average":[204,209],"precision":[205],"31%":[207],"recall":[210],"53%":[212],"when":[213],"tested":[214],"against":[215],"manually":[216],"assigned":[217]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":3},{"year":2019,"cited_by_count":8},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}