{"id":"https://openalex.org/W2810436815","doi":"https://doi.org/10.1017/s1351324918000244","title":"Multilingual SMS-based author profiling: Data and methods","display_name":"Multilingual SMS-based author profiling: Data and methods","publication_year":2018,"publication_date":"2018-06-26","ids":{"openalex":"https://openalex.org/W2810436815","doi":"https://doi.org/10.1017/s1351324918000244","mag":"2810436815"},"language":"en","primary_location":{"id":"doi:10.1017/s1351324918000244","is_oa":false,"landing_page_url":"https://doi.org/10.1017/s1351324918000244","pdf_url":null,"source":{"id":"https://openalex.org/S18088403","display_name":"Natural Language Engineering","issn_l":"1351-3249","issn":["1351-3249","1469-8110"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311721","host_organization_name":"Cambridge University Press","host_organization_lineage":["https://openalex.org/P4310311721","https://openalex.org/P4310311702"],"host_organization_lineage_names":["Cambridge University Press","University of Cambridge"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Natural Language Engineering","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/A5000215482","display_name":"Mehwish Fatima","orcid":"https://orcid.org/0000-0003-3424-2991"},"institutions":[{"id":"https://openalex.org/I16076960","display_name":"COMSATS University Islamabad","ror":"https://ror.org/00nqqvk19","country_code":"PK","type":"education","lineage":["https://openalex.org/I16076960"]}],"countries":["PK"],"is_corresponding":true,"raw_author_name":"MEHWISH FATIMA","raw_affiliation_strings":["Department of Computer Science, COMSATS University Islamabad, Lahore Campus, Pakistan e-mails:"],"raw_orcid":"https://orcid.org/0000-0003-3424-2991","affiliations":[{"raw_affiliation_string":"Department of Computer Science, COMSATS University Islamabad, Lahore Campus, Pakistan e-mails:","institution_ids":["https://openalex.org/I16076960"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081317961","display_name":"Saba Anwar","orcid":"https://orcid.org/0000-0003-1265-9809"},"institutions":[{"id":"https://openalex.org/I16076960","display_name":"COMSATS University Islamabad","ror":"https://ror.org/00nqqvk19","country_code":"PK","type":"education","lineage":["https://openalex.org/I16076960"]}],"countries":["PK"],"is_corresponding":false,"raw_author_name":"SABA ANWAR","raw_affiliation_strings":["Department of Computer Science, COMSATS University Islamabad, Lahore Campus, Pakistan e-mails:"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, COMSATS University Islamabad, Lahore Campus, Pakistan e-mails:","institution_ids":["https://openalex.org/I16076960"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074646159","display_name":"Amna Naveed","orcid":null},"institutions":[{"id":"https://openalex.org/I16076960","display_name":"COMSATS University Islamabad","ror":"https://ror.org/00nqqvk19","country_code":"PK","type":"education","lineage":["https://openalex.org/I16076960"]}],"countries":["PK"],"is_corresponding":false,"raw_author_name":"AMNA NAVEED","raw_affiliation_strings":["Department of Computer Science, COMSATS University Islamabad, Lahore Campus, Pakistan e-mails:"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, COMSATS University Islamabad, Lahore Campus, Pakistan e-mails:","institution_ids":["https://openalex.org/I16076960"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108213958","display_name":"Waqas Arshad","orcid":null},"institutions":[{"id":"https://openalex.org/I4210100043","display_name":"Superior University","ror":"https://ror.org/00yh88643","country_code":"PK","type":"education","lineage":["https://openalex.org/I4210100043"]}],"countries":["PK"],"is_corresponding":false,"raw_author_name":"WAQAS ARSHAD","raw_affiliation_strings":["Department of Computer Science & IT, Superior University, Lahore, Pakistan e-mail:"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science & IT, Superior University, Lahore, Pakistan e-mail:","institution_ids":["https://openalex.org/I4210100043"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005027058","display_name":"Rao Muhammad Adeel Nawab","orcid":"https://orcid.org/0000-0002-1765-8904"},"institutions":[{"id":"https://openalex.org/I16076960","display_name":"COMSATS University Islamabad","ror":"https://ror.org/00nqqvk19","country_code":"PK","type":"education","lineage":["https://openalex.org/I16076960"]}],"countries":["PK"],"is_corresponding":false,"raw_author_name":"RAO MUHAMMAD ADEEL NAWAB","raw_affiliation_strings":["Department of Computer Science, COMSATS University Islamabad, Lahore Campus, Pakistan e-mails:"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, COMSATS University Islamabad, Lahore Campus, Pakistan e-mails:","institution_ids":["https://openalex.org/I16076960"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005033313","display_name":"Muntaha Iqbal","orcid":null},"institutions":[{"id":"https://openalex.org/I142732210","display_name":"University of Engineering and Technology Lahore","ror":"https://ror.org/0051w2v06","country_code":"PK","type":"education","lineage":["https://openalex.org/I142732210"]}],"countries":["PK"],"is_corresponding":false,"raw_author_name":"MUNTAHA IQBAL","raw_affiliation_strings":["Al-Khwarizmi Institute of Computer Science, University of Engineering & Technology, Lahore, Pakistan e-mail:"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Al-Khwarizmi Institute of Computer Science, University of Engineering & Technology, Lahore, Pakistan e-mail:","institution_ids":["https://openalex.org/I142732210"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061509344","display_name":"ALIA MASOOD","orcid":null},"institutions":[{"id":"https://openalex.org/I16076960","display_name":"COMSATS University Islamabad","ror":"https://ror.org/00nqqvk19","country_code":"PK","type":"education","lineage":["https://openalex.org/I16076960"]}],"countries":["PK"],"is_corresponding":false,"raw_author_name":"ALIA MASOOD","raw_affiliation_strings":["Department of Computer Science, COMSATS University Islamabad, Lahore Campus, Pakistan e-mails:"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, COMSATS University Islamabad, Lahore Campus, Pakistan e-mails:","institution_ids":["https://openalex.org/I16076960"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5000215482"],"corresponding_institution_ids":["https://openalex.org/I16076960"],"apc_list":null,"apc_paid":null,"fwci":1.3538,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.85800121,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"24","issue":"5","first_page":"695","last_page":"724"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12380","display_name":"Authorship Attribution and Profiling","score":1.0,"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":1.0,"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/T13155","display_name":"Digital Communication and Language","score":0.9987999796867371,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/T12262","display_name":"Hate Speech and Cyberbullying Detection","score":0.9933000206947327,"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/computer-science","display_name":"Computer science","score":0.8548966646194458},{"id":"https://openalex.org/keywords/stylometry","display_name":"Stylometry","score":0.826784610748291},{"id":"https://openalex.org/keywords/profiling","display_name":"Profiling (computer programming)","score":0.7934592366218567},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6428601741790771},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.546419084072113},{"id":"https://openalex.org/keywords/short-message-service","display_name":"Short Message Service","score":0.515540599822998},{"id":"https://openalex.org/keywords/social-media","display_name":"Social media","score":0.46356046199798584},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3980862498283386},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3768260180950165}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8548966646194458},{"id":"https://openalex.org/C11192451","wikidata":"https://www.wikidata.org/wiki/Q2032038","display_name":"Stylometry","level":2,"score":0.826784610748291},{"id":"https://openalex.org/C187191949","wikidata":"https://www.wikidata.org/wiki/Q1138496","display_name":"Profiling (computer programming)","level":2,"score":0.7934592366218567},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6428601741790771},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.546419084072113},{"id":"https://openalex.org/C74558129","wikidata":"https://www.wikidata.org/wiki/Q43024","display_name":"Short Message Service","level":2,"score":0.515540599822998},{"id":"https://openalex.org/C518677369","wikidata":"https://www.wikidata.org/wiki/Q202833","display_name":"Social media","level":2,"score":0.46356046199798584},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3980862498283386},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3768260180950165},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1017/s1351324918000244","is_oa":false,"landing_page_url":"https://doi.org/10.1017/s1351324918000244","pdf_url":null,"source":{"id":"https://openalex.org/S18088403","display_name":"Natural Language Engineering","issn_l":"1351-3249","issn":["1351-3249","1469-8110"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311721","host_organization_name":"Cambridge University Press","host_organization_lineage":["https://openalex.org/P4310311721","https://openalex.org/P4310311702"],"host_organization_lineage_names":["Cambridge University Press","University of Cambridge"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Natural Language Engineering","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4399999976158142,"display_name":"Gender equality","id":"https://metadata.un.org/sdg/5"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320609","display_name":"University of Tasmania","ror":"https://ror.org/01nfmeh72"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":83,"referenced_works":["https://openalex.org/W9292421","https://openalex.org/W16472989","https://openalex.org/W87681983","https://openalex.org/W172260869","https://openalex.org/W1211014924","https://openalex.org/W1541992550","https://openalex.org/W1569596443","https://openalex.org/W1570448133","https://openalex.org/W1673133728","https://openalex.org/W1696750187","https://openalex.org/W1914856875","https://openalex.org/W1984010941","https://openalex.org/W1988906723","https://openalex.org/W1993410732","https://openalex.org/W1997060558","https://openalex.org/W2001346904","https://openalex.org/W2025153046","https://openalex.org/W2032793012","https://openalex.org/W2035324701","https://openalex.org/W2037532099","https://openalex.org/W2037615273","https://openalex.org/W2038178664","https://openalex.org/W2043500582","https://openalex.org/W2068192101","https://openalex.org/W2071629922","https://openalex.org/W2095621640","https://openalex.org/W2100304601","https://openalex.org/W2100578792","https://openalex.org/W2110302976","https://openalex.org/W2116216325","https://openalex.org/W2135345655","https://openalex.org/W2136264427","https://openalex.org/W2140907953","https://openalex.org/W2152451111","https://openalex.org/W2153429513","https://openalex.org/W2155652813","https://openalex.org/W2156413587","https://openalex.org/W2156985793","https://openalex.org/W2157324335","https://openalex.org/W2165214536","https://openalex.org/W2165431734","https://openalex.org/W2170505850","https://openalex.org/W2171688411","https://openalex.org/W2179658543","https://openalex.org/W2203890649","https://openalex.org/W2250792670","https://openalex.org/W2293266173","https://openalex.org/W2294270621","https://openalex.org/W2317645432","https://openalex.org/W2397921183","https://openalex.org/W2398136829","https://openalex.org/W2398186482","https://openalex.org/W2402430665","https://openalex.org/W2405732212","https://openalex.org/W2406530401","https://openalex.org/W2435251607","https://openalex.org/W2488557833","https://openalex.org/W2519858746","https://openalex.org/W2571811767","https://openalex.org/W2575120141","https://openalex.org/W2575864632","https://openalex.org/W2582664174","https://openalex.org/W2584455886","https://openalex.org/W2584997055","https://openalex.org/W2585583534","https://openalex.org/W2606066802","https://openalex.org/W2749398986","https://openalex.org/W2752530998","https://openalex.org/W2979815100","https://openalex.org/W3099138433","https://openalex.org/W3103503062","https://openalex.org/W6600376888","https://openalex.org/W6600663431","https://openalex.org/W6627915109","https://openalex.org/W6637445175","https://openalex.org/W6676670208","https://openalex.org/W6680863764","https://openalex.org/W6682733454","https://openalex.org/W6682858398","https://openalex.org/W6732114941","https://openalex.org/W6784997385","https://openalex.org/W7019759554","https://openalex.org/W7070182289"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2895461980","https://openalex.org/W2187670843","https://openalex.org/W2027650462","https://openalex.org/W2768755876","https://openalex.org/W2285499887","https://openalex.org/W2155953932","https://openalex.org/W2187360386","https://openalex.org/W2619884807","https://openalex.org/W3007882868"],"abstract_inverted_index":{"Abstract":[0],"In":[1],"the":[2,126,130,137,152,160,180,193,200,205,221],"recent":[3],"years,":[4],"many":[5],"benchmark":[6,68],"author":[7,50,70,78,105,186],"profiling":[8,71,187],"corpora":[9,227],"have":[10],"been":[11,33],"developed":[12,34],"for":[13,35,49,133,147,165,179,216,237],"various":[14,185],"genres":[15],"including":[16],"Twitter,":[17],"social":[18],"media,":[19],"blogs,":[20],"hotel":[21],"reviews":[22],"and":[23,65,115,149,159,182,210,229,234],"e-mail,":[24],"etc.":[25],"However,":[26],"no":[27],"such":[28],"standard":[29],"evaluation":[30,183],"resource":[31],"has":[32],"Short":[36],"Messaging":[37],"Service":[38],"(SMS),":[39],"a":[40,61,91],"popular":[41],"medium":[42],"of":[43,55,84,87,94,122,156,184,208,214],"communication,":[44],"which":[45],"is":[46,58],"very":[47],"useful":[48],"profiling.":[51],"The":[52,73,119,189],"primary":[53],"aim":[54],"this":[56,123],"study":[57,124],"to":[59,170],"develop":[60],"large":[62],"multilingual":[63],"(English":[64],"Roman":[66],"Urdu)":[67],"SMS-based":[69],"corpus.":[72,223],"proposed":[74,131,174,226],"corpus":[75,132,175],"contains":[76],"810":[77],"profiles,":[79],"wherein":[80],"each":[81,104],"profile":[82],"consists":[83],"an":[85,95],"aggregation":[86],"SMS":[88],"messages":[89],"as":[90],"single":[92],"document":[93],"author,":[96],"along":[97],"with":[98,103],"seven":[99],"demographic":[100],"traits":[101],"associated":[102],"profile:":[106],"gender,":[107],"age,":[108],"native":[109,111],"language,":[110],"city,":[112],"qualification,":[113],"occupation":[114],"personality":[116],"type":[117],"(introvert/extrovert).":[118],"secondary":[120],"aims":[121],"include":[125],"following:":[127],"(1)":[128],"annotating":[129],"code-switching":[134],"annotations":[135],"at":[136],"lexical":[138],"level":[139],"(approximately":[140],"0.69":[141],"million":[142],"tokens":[143],"are":[144,232],"manually":[145],"annotated":[146],"code-switching)":[148],"(2)":[150],"applying":[151],"stylometry-based":[153],"method":[154,162],"(groups":[155],"sixty-four":[157],"features)":[158,164],"content-based":[161,194],"(twelve":[163],"gender":[166,217],"identification":[167,218],"in":[168],"order":[169],"demonstrate":[171],"how":[172],"our":[173,225],"can":[176],"be":[177],"used":[178],"development":[181],"methods.":[188],"results":[190],"show":[191],"that":[192],"character":[195],"5-gram":[196],"feature":[197],"outperformed":[198],"all":[199],"other":[201],"features":[202],"by":[203],"obtaining":[204],"accuracy":[206],"score":[207,213],"0.975":[209],"F":[211],"1":[212],"0.947":[215],"while":[219],"using":[220],"entire":[222],"Furthermore,":[224],"(SMS\u2013AP\u201318":[228],"code-switched":[230],"SMS\u2013AP\u201318)":[231],"freely":[233],"publicly":[235],"available":[236],"research":[238],"purpose.":[239]},"counts_by_year":[{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}