{"id":"https://openalex.org/W7204648077","doi":"https://doi.org/10.5281/zenodo.22159648","title":"BanglishChat: A Human vs. AI-Generated Banglish Chat Dataset for AI-Text and Impersonation-Scam Detection","display_name":"BanglishChat: A Human vs. AI-Generated Banglish Chat Dataset for AI-Text and Impersonation-Scam Detection","publication_year":2026,"publication_date":"2026-08-29","ids":{"openalex":"https://openalex.org/W7204648077","doi":"https://doi.org/10.5281/zenodo.22159648"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.22159648","doi":"https://doi.org/10.5281/zenodo.22159648","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.22159648","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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"},"parent_works":[],"lineage":["https://openalex.org/W7204648077"],"child_works_count":0,"type":"dataset","is_traditional":false,"indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.22159648","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5148602490","display_name":"MD Sozon","orcid":"https://orcid.org/0009-0001-9588-0949","observed_orcids":["https://orcid.org/0009-0001-9588-0949"]},"institutions":[{"id":"https://openalex.org/I233772129","display_name":"Dhaka International University","ror":"https://ror.org/05nsh7a69","country_code":"BD","type":"education","lineage":["https://openalex.org/I233772129"]}],"countries":["BD"],"is_corresponding":false,"raw_author_name":"Sozon, MD","raw_affiliation_strings":["Dhaka International University"],"raw_orcid":"https://orcid.org/0009-0001-9588-0949","affiliations":[{"raw_affiliation_string":"Dhaka International University","institution_ids":["https://openalex.org/I233772129"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148606847","display_name":"Raju Md. Humayun Kabir","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I233772129","display_name":"Dhaka International University","ror":"https://ror.org/05nsh7a69","country_code":"BD","type":"education","lineage":["https://openalex.org/I233772129"]}],"countries":["BD"],"is_corresponding":false,"raw_author_name":"Md. Humayun Kabir, Raju","raw_affiliation_strings":["Dhaka International University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dhaka International University","institution_ids":["https://openalex.org/I233772129"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148585740","display_name":"Md. Soleman","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I233772129","display_name":"Dhaka International University","ror":"https://ror.org/05nsh7a69","country_code":"BD","type":"education","lineage":["https://openalex.org/I233772129"]}],"countries":["BD"],"is_corresponding":false,"raw_author_name":"Soleman, Md.","raw_affiliation_strings":["Dhaka International University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dhaka International University","institution_ids":["https://openalex.org/I233772129"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148591105","display_name":"Hossain Md. Saif","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I233772129","display_name":"Dhaka International University","ror":"https://ror.org/05nsh7a69","country_code":"BD","type":"education","lineage":["https://openalex.org/I233772129"]}],"countries":["BD"],"is_corresponding":false,"raw_author_name":"Md. Saif, Hossain","raw_affiliation_strings":["Dhaka International University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dhaka International University","institution_ids":["https://openalex.org/I233772129"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5148603299","display_name":"Md. Asifuzzamman","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I233772129","display_name":"Dhaka International University","ror":"https://ror.org/05nsh7a69","country_code":"BD","type":"education","lineage":["https://openalex.org/I233772129"]}],"countries":["BD"],"is_corresponding":false,"raw_author_name":"Asifuzzamman, Md.","raw_affiliation_strings":["Dhaka International University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dhaka International University","institution_ids":["https://openalex.org/I233772129"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I233772129"],"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":false,"primary_topic":{"id":"https://openalex.org/T12380","display_name":"Authorship Attribution and Profiling","score":0.9779999852180481,"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/T12380","display_name":"Authorship Attribution and Profiling","score":0.9779999852180481,"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/T11644","display_name":"Spam and Phishing Detection","score":0.014999999664723873,"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"}},{"id":"https://openalex.org/T11147","display_name":"Misinformation and Its Impacts","score":0.0007999999797903001,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/banglish","display_name":"Banglish","score":0.9860000014305115},{"id":"https://openalex.org/keywords/code-mixing","display_name":"code-mixing","score":0.7829999923706055},{"id":"https://openalex.org/keywords/ai-generated-text-detection","display_name":"AI-generated text detection","score":0.9679999947547913},{"id":"https://openalex.org/keywords/human-vs-ai-text-classification","display_name":"human vs AI text classification","score":0.6380000114440918},{"id":"https://openalex.org/keywords/low-resource-nlp","display_name":"low-resource NLP","score":0.6349999904632568},{"id":"https://openalex.org/keywords/fraud-detection","display_name":"fraud detection","score":0.609000027179718}],"concepts":[{"id":"https://openalex.org/C2776809875","wikidata":"https://www.wikidata.org/wiki/Q1375963","display_name":"Converse","level":2,"score":0.771399974822998},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6894000172615051},{"id":"https://openalex.org/C2780551164","wikidata":"https://www.wikidata.org/wiki/Q2306599","display_name":"Column (typography)","level":3,"score":0.566100001335144},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.47699999809265137},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4754999876022339},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.39149999618530273},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.349700003862381},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3215000033378601},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.31540000438690186},{"id":"https://openalex.org/C169093310","wikidata":"https://www.wikidata.org/wiki/Q3702971","display_name":"Personally identifiable information","level":2,"score":0.3122999966144562},{"id":"https://openalex.org/C135598885","wikidata":"https://www.wikidata.org/wiki/Q1366302","display_name":"Row","level":2,"score":0.3107999861240387},{"id":"https://openalex.org/C13622073","wikidata":"https://www.wikidata.org/wiki/Q2243831","display_name":"Writing style","level":2,"score":0.2987000048160553},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.28139999508857727},{"id":"https://openalex.org/C2987082051","wikidata":"https://www.wikidata.org/wiki/Q223642","display_name":"Human interaction","level":2,"score":0.27810001373291016},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2727000117301941},{"id":"https://openalex.org/C11192451","wikidata":"https://www.wikidata.org/wiki/Q2032038","display_name":"Stylometry","level":2,"score":0.2630000114440918}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5281/zenodo.22159648","doi":"https://doi.org/10.5281/zenodo.22159648","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.22159648","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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"},{"id":"doi:10.5281/zenodo.22159649","doi":"https://doi.org/10.5281/zenodo.22159649","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.22159649","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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"}],"best_oa_location":{"id":"doi:10.5281/zenodo.22159648","doi":"https://doi.org/10.5281/zenodo.22159648","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.22159648","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7083682593","https://openalex.org/W7214032324","https://openalex.org/W7172259838","https://openalex.org/W7078790119","https://openalex.org/W4414604998","https://openalex.org/W7163125540","https://openalex.org/W7167236288","https://openalex.org/W6936264937","https://openalex.org/W4411172390","https://openalex.org/W7223083348"],"abstract_inverted_index":{"This":[0,80,169],"dataset":[1,81,170],"supports":[2,82],"research":[3,160],"on":[4,161],"detecting":[5],"AI-generated":[6,91,112],"text":[7,152],"in":[8,25,45,97,126,136,146,164],"Banglish":[9,46,63,92,107,113],"(Bangla":[10],"written":[11],"using":[12],"Latin/English":[13],"characters),":[14],"a":[15,98],"code-mixed":[16],"writing":[17],"style":[18],"widely":[19],"used":[20],"for":[21,154],"everyday":[22],"digital":[23,167],"communication":[24],"Bangladesh.":[26],"Motivation:":[27],"fraudsters":[28],"increasingly":[29],"use":[30],"AI":[31],"chatbots":[32],"(e.g.,":[33],"ChatGPT,":[34,118],"DeepSeek,":[35,119],"Gemini,":[36,120],"Grok)":[37],"to":[38,49,67,78,123],"impersonate":[39],"friends,":[40],"relatives,":[41],"or":[42,57,70,185],"institutional":[43],"representatives":[44],"SMS/chat":[47],"conversations":[48],"build":[50],"trust,":[51],"then":[52],"extract":[53],"money,":[54],"credentials":[55],"(OTP/PIN/passwords),":[56],"sensitive":[58],"personal":[59],"information":[60],"from":[61,90],"victims.":[62],"is":[64],"under-studied":[65],"compared":[66],"standard":[68],"Bangla":[69],"English,":[71],"so":[72],"existing":[73],"AI-text-detection":[74],"tools":[75],"generalize":[76],"poorly":[77],"it.":[79],"building":[83],"and":[84,109,121,131,142,159],"evaluating":[85],"classifiers":[86,153],"that":[87],"distinguish":[88],"human-written":[89,106],"text.":[93],"Contents:":[94],"8,389":[95],"rows":[96],"CSV":[99],"with":[100],"two":[101],"columns":[102],"\u2014":[103],"Human_chat":[104],"(6,991":[105],"messages)":[108],"AI_chat":[110],"(7,976":[111],"messages,":[114],"produced":[115],"by":[116],"prompting":[117],"Grok":[122],"converse":[124],"casually":[125],"Banglish).":[127],"Full":[128],"column":[129],"definitions":[130],"summary":[132],"statistics":[133],"are":[134,145],"provided":[135],"the":[137,181],"accompanying":[138],"DATA_DICTIONARY.md;":[139],"usage":[140],"notes":[141],"known":[143],"limitations":[144],"README.md.":[147],"Intended":[148],"use:":[149],"training/evaluating":[150],"human-vs-AI":[151],"Banglish,":[155],"code-mixed/low-resource":[156],"NLP":[157],"research,":[158],"impersonation-scam":[162],"detection":[163],"South":[165],"Asian":[166],"communication.":[168],"does":[171],"not":[172],"itself":[173],"label":[174],"messages":[175],"as":[176],"fraudulent;":[177],"it":[178],"labels":[179],"only":[180],"authorship":[182],"source":[183],"(human":[184],"AI).":[186]},"counts_by_year":[],"updated_date":"2026-10-08T09:06:37.294493","created_date":"2026-08-30T00:00:00"}