{"id":"https://openalex.org/W6907235994","doi":"https://doi.org/10.21227/y77y-9917","title":"\"Urdu Human and AI text Dataset (UHAT)\"","display_name":"\"Urdu Human and AI text Dataset (UHAT)\"","publication_year":2025,"publication_date":"2025-07-20","ids":{"openalex":"https://openalex.org/W6907235994","doi":"https://doi.org/10.21227/y77y-9917"},"language":"en","primary_location":{"id":"doi:10.21227/y77y-9917","is_oa":true,"landing_page_url":"https://doi.org/10.21227/y77y-9917","pdf_url":null,"source":{"id":"https://openalex.org/S7407051695","display_name":"IEEE DataPort","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"},"type":"dataset","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.21227/y77y-9917","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Muhammad Ammar","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Muhammad Ammar","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":null,"topics":[],"keywords":[{"id":"https://openalex.org/keywords/rewriting","display_name":"Rewriting","score":0.7470999956130981},{"id":"https://openalex.org/keywords/urdu","display_name":"Urdu","score":0.6963000297546387},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5717999935150146},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5623000264167786},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.38119998574256897},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.3723999857902527}],"concepts":[{"id":"https://openalex.org/C154690210","wikidata":"https://www.wikidata.org/wiki/Q1668499","display_name":"Rewriting","level":2,"score":0.7470999956130981},{"id":"https://openalex.org/C2777350258","wikidata":"https://www.wikidata.org/wiki/Q1617","display_name":"Urdu","level":2,"score":0.6963000297546387},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6693999767303467},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.607699990272522},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5871000289916992},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5717999935150146},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5623000264167786},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.38119998574256897},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3723999857902527},{"id":"https://openalex.org/C175293574","wikidata":"https://www.wikidata.org/wiki/Q697133","display_name":"Word lists by frequency","level":3,"score":0.37139999866485596},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.3546999990940094},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.3538999855518341},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.325300008058548},{"id":"https://openalex.org/C203763787","wikidata":"https://www.wikidata.org/wiki/Q371029","display_name":"Null (SQL)","level":2,"score":0.31369999051094055},{"id":"https://openalex.org/C148524875","wikidata":"https://www.wikidata.org/wiki/Q6975395","display_name":"F1 score","level":2,"score":0.2978000044822693},{"id":"https://openalex.org/C3019641298","wikidata":"https://www.wikidata.org/wiki/Q625642","display_name":"Word length","level":2,"score":0.2766999900341034}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21227/y77y-9917","is_oa":true,"landing_page_url":"https://doi.org/10.21227/y77y-9917","pdf_url":null,"source":{"id":"https://openalex.org/S7407051695","display_name":"IEEE DataPort","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Dataset"}],"best_oa_location":{"id":"doi:10.21227/y77y-9917","is_oa":true,"landing_page_url":"https://doi.org/10.21227/y77y-9917","pdf_url":null,"source":{"id":"https://openalex.org/S7407051695","display_name":"IEEE DataPort","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6403476595878601}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"\"Dataset":[0],"Overview This":[1],"dataset":[2,20,103],"is":[3,104,153,160],"designed":[4],"for":[5,10,144,157],"Urdu":[6,62],"text":[7,26,152,185,193],"classification,":[8],"specifically":[9],"distinguishing":[11],"between":[12],"human-written":[13,52,79,166],"and":[14,98,189],"AI-generated":[15,72,145,178],"text.":[16],"It's":[17],"a":[18,22,57,115,134,150,169],"balanced":[19],"containing":[21],"total":[23,116],"of":[24,60,94,117,137,149],"3600":[25],"samples.Human-Written":[27],"Texts:":[28,39],"1800":[29,40],"samples":[30,41],"written":[31],"by":[32,43,76],"humans.":[33],"These":[34,46],"are":[35,47,114],"labeled":[36,48],"with":[37,49,106,133],"0.AI-Generated":[38],"generated":[42],"AI":[44,158,192],"models.":[45],"1. Data":[50],"Sources The":[51],"texts":[53,73,80,126,167,179],"were":[54,74],"collected":[55],"from":[56],"diverse":[58],"range":[59],"reputable":[61],"sources,":[63],"including:Urdu":[64],"literature":[65],"(stories,":[66],"novels)rekhta.orgBBC":[67],"UrduVOA":[68],"UrduUrdu":[69],"WikipediaNews":[70],"ArticlesThe":[71],"created":[75],"rewriting":[77],"the":[78,82,95,122,190],"using":[81],"following":[83],"models:GPTGeminiKimiData":[84],"Quality":[85],"&":[86],"CharacteristicsThe":[87],"EDA":[88],"notebook":[89],"reveals":[90],"several":[91],"key":[92],"aspects":[93],"data's":[96],"quality":[97],"structure:No":[99],"Missing":[100],"Values:":[101],"The":[102],"clean,":[105],"no":[107],"null":[108],"values":[109],"or":[110],"empty":[111],"strings.Duplicates:":[112],"There":[113],"8":[118],"duplicate":[119],"entries":[120],"in":[121],"combined":[123],"dataset.Text":[124],"Length:Human-written":[125],"tend":[127],"to":[128,142,163],"be":[129],"longer":[130],"on":[131],"average,":[132],"mean":[135],"length":[136,148],"approximately":[138],"889":[139],"characters,":[140,155],"compared":[141],"748":[143],"texts.The":[146],"maximum":[147],"human":[151,184],"12,754":[154],"while":[156],"it":[159],"6,762.Word":[161],"Count:Similar":[162],"character":[164],"length,":[165],"have":[168],"higher":[170],"average":[171],"word":[172],"count":[173],"(around":[174,180],"198":[175],"words)":[176],"than":[177],"165":[181],"words).The":[182],"longest":[183,191],"has":[186,194],"3016":[187],"words,":[188],"1464":[195],"words.TEXT":[196],"FEATURE":[197],"ANALYSIS:Character":[198],"Distribution: Word-level":[199],"Analysis:N-Gram":[200],"Analysis:TEXT":[201],"COMPLEXITY":[202],"ANALYSISVocabulary":[203],"Analysis:\"":[204]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2025-10-10T00:00:00"}