{"id":"https://openalex.org/W4400808506","doi":"https://doi.org/10.3390/info15070419","title":"Toward Robust Arabic AI-Generated Text Detection: Tackling Diacritics Challenges","display_name":"Toward Robust Arabic AI-Generated Text Detection: Tackling Diacritics Challenges","publication_year":2024,"publication_date":"2024-07-19","ids":{"openalex":"https://openalex.org/W4400808506","doi":"https://doi.org/10.3390/info15070419"},"language":"en","primary_location":{"id":"doi:10.3390/info15070419","is_oa":true,"landing_page_url":"https://doi.org/10.3390/info15070419","pdf_url":null,"source":{"id":"https://openalex.org/S4210219776","display_name":"Information","issn_l":"2078-2489","issn":["2078-2489"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Information","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.3390/info15070419","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102580418","display_name":"Hamed Alshammari","orcid":null},"institutions":[{"id":"https://openalex.org/I154300980","display_name":"University of Bridgeport","ror":"https://ror.org/01rf3yp57","country_code":"US","type":"education","lineage":["https://openalex.org/I154300980"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hamed Alshammari","raw_affiliation_strings":["Department of Computer Science and Engineering, University of Bridgeport, Bridgeport, CT 06604, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, University of Bridgeport, Bridgeport, CT 06604, USA","institution_ids":["https://openalex.org/I154300980"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070765307","display_name":"Khaled Elleithy","orcid":"https://orcid.org/0000-0001-9239-5035"},"institutions":[{"id":"https://openalex.org/I154300980","display_name":"University of Bridgeport","ror":"https://ror.org/01rf3yp57","country_code":"US","type":"education","lineage":["https://openalex.org/I154300980"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Khaled Elleithy","raw_affiliation_strings":["Department of Computer Science and Engineering, University of Bridgeport, Bridgeport, CT 06604, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, University of Bridgeport, Bridgeport, CT 06604, USA","institution_ids":["https://openalex.org/I154300980"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5070765307"],"corresponding_institution_ids":["https://openalex.org/I154300980"],"apc_list":{"value":1400,"currency":"CHF","value_usd":1515},"apc_paid":{"value":1400,"currency":"CHF","value_usd":1515},"fwci":2.418,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.90154281,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"15","issue":"7","first_page":"419","last_page":"419"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998000264167786,"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":0.9998000264167786,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9993000030517578,"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":0.9779000282287598,"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/arabic","display_name":"Arabic","score":0.7427339553833008},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5419564843177795},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4953871965408325},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.48958954215049744},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.31210213899612427},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.14575007557868958}],"concepts":[{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.7427339553833008},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5419564843177795},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4953871965408325},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.48958954215049744},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.31210213899612427},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.14575007557868958}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3390/info15070419","is_oa":true,"landing_page_url":"https://doi.org/10.3390/info15070419","pdf_url":null,"source":{"id":"https://openalex.org/S4210219776","display_name":"Information","issn_l":"2078-2489","issn":["2078-2489"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Information","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:6502b2defbdd4f8c9a358399266efb87","is_oa":true,"landing_page_url":"https://doaj.org/article/6502b2defbdd4f8c9a358399266efb87","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Information, Vol 15, Iss 7, p 419 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3390/info15070419","is_oa":true,"landing_page_url":"https://doi.org/10.3390/info15070419","pdf_url":null,"source":{"id":"https://openalex.org/S4210219776","display_name":"Information","issn_l":"2078-2489","issn":["2078-2489"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Information","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.8600000143051147}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1984708705","https://openalex.org/W2147272182","https://openalex.org/W2471147443","https://openalex.org/W2950681488","https://openalex.org/W2963748441","https://openalex.org/W2986154550","https://openalex.org/W3032746405","https://openalex.org/W3035390927","https://openalex.org/W3103187652","https://openalex.org/W3106580412","https://openalex.org/W3129207397","https://openalex.org/W3149627794","https://openalex.org/W3174685870","https://openalex.org/W4283170666","https://openalex.org/W4292779060","https://openalex.org/W4309197038","https://openalex.org/W4313294616","https://openalex.org/W4318672916","https://openalex.org/W4321116084","https://openalex.org/W4324046518","https://openalex.org/W4366390252","https://openalex.org/W4385694164","https://openalex.org/W4388704363","https://openalex.org/W4390986274","https://openalex.org/W4392913295","https://openalex.org/W4392946376","https://openalex.org/W4398777040","https://openalex.org/W4399073714","https://openalex.org/W6681530644","https://openalex.org/W6778883912"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W4249048193","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Current":[0],"AI":[1],"detection":[2,37,102,113,181],"systems":[3],"often":[4],"struggle":[5],"to":[6,18,53,85,94,108,121,125,176,198,207],"distinguish":[7],"between":[8],"Arabic":[9,27,35,70,196],"human-written":[10],"text":[11,15,28,36],"(HWT)":[12],"and":[13,24,47,58,80,88,98,152,179],"AI-generated":[14],"(AIGT)":[16],"due":[17,197],"the":[19,26,60,64,96,101,129,143,146,158,180],"small":[20],"marks":[21],"present":[22],"above":[23],"below":[25],"called":[29],"diacritics.":[30],"This":[31],"study":[32],"introduces":[33],"robust":[34],"models":[38,103,114,182],"using":[39],"Transformer-based":[40],"pre-trained":[41],"models,":[42],"specifically":[43],"AraELECTRA,":[44],"AraBERT,":[45],"XLM-R,":[46],"mBERT.":[48],"Our":[49,112,133],"primary":[50],"goal":[51],"is":[52,155,205],"detect":[54],"AIGTs":[55],"in":[56,69,140],"essays":[57],"overcome":[59],"challenges":[61],"posed":[62],"by":[63],"diacritics":[65,139,154],"that":[66],"usually":[67],"appear":[68],"religious":[71],"texts.":[72],"We":[73,92],"created":[74],"several":[75],"novel":[76],"datasets":[77,107],"with":[78,151],"diacritized":[79,117,147,185],"non-diacritized":[81],"texts":[82],"comprising":[83],"up":[84,120],"9666":[86],"HWT":[87],"AIGT":[89],"training":[90,141],"examples.":[91],"aimed":[93],"assess":[95,109],"robustness":[97],"effectiveness":[99],"of":[100,145],"on":[104,116,128,184,195],"out-of-domain":[105],"(OOD)":[106],"their":[110],"generalizability.":[111],"trained":[115,183],"examples":[118,150,186],"achieved":[119],"98.4%":[122],"accuracy":[123,160],"compared":[124,175],"GPTZero\u2019s":[126],"62.7%":[127],"AIRABIC":[130],"benchmark":[131],"dataset.":[132],"experiments":[134],"reveal":[135],"that,":[136],"while":[137],"including":[138],"enhances":[142],"recognition":[144],"HWTs,":[148],"duplicating":[149],"without":[153,189],"inefficient":[156],"despite":[157],"high":[159],"achieved.":[161],"Applying":[162],"a":[163],"dediacritization":[164],"filter":[165],"during":[166],"evaluation":[167],"significantly":[168],"improved":[169],"model":[170],"performance,":[171],"achieving":[172],"optimal":[173],"performance":[174],"both":[177],"GPTZero":[178],"but":[187],"evaluated":[188],"dediacritization.":[190],"Although":[191],"our":[192,202],"focus":[193],"was":[194],"its":[199],"writing":[200],"challenges,":[201],"detector":[203],"architecture":[204],"adaptable":[206],"any":[208],"language.":[209]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6}],"updated_date":"2026-04-02T15:55:50.835912","created_date":"2025-10-10T00:00:00"}