{"id":"https://openalex.org/W4413772162","doi":"https://doi.org/10.1007/s13278-025-01505-z","title":"Addressing data scarcity in multilingual fake news detection: an LLM-based dataset augmentation approach","display_name":"Addressing data scarcity in multilingual fake news detection: an LLM-based dataset augmentation approach","publication_year":2025,"publication_date":"2025-08-28","ids":{"openalex":"https://openalex.org/W4413772162","doi":"https://doi.org/10.1007/s13278-025-01505-z"},"language":"en","primary_location":{"id":"doi:10.1007/s13278-025-01505-z","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s13278-025-01505-z","pdf_url":"https://link.springer.com/content/pdf/10.1007/s13278-025-01505-z.pdf","source":{"id":"https://openalex.org/S2764891196","display_name":"Social Network Analysis and Mining","issn_l":"1869-5450","issn":["1869-5450","1869-5469"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Social Network Analysis and Mining","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s13278-025-01505-z.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5094038606","display_name":"Razieh Chalehchaleh","orcid":null},"institutions":[{"id":"https://openalex.org/I4210145102","display_name":"Institut Polytechnique de Paris","ror":"https://ror.org/042tfbd02","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210145102"]},{"id":"https://openalex.org/I4387153010","display_name":"T\u00e9l\u00e9com SudParis","ror":"https://ror.org/05xvk4r52","country_code":"FR","type":"education","lineage":["https://openalex.org/I205703379","https://openalex.org/I4210145102","https://openalex.org/I4387153010"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Razieh Chalehchaleh","raw_affiliation_strings":["SAMOVAR, T\u00e9l\u00e9com SudParis, Institut Polytechnique de Paris, Palaiseau, 91120, France","IP Paris - Institut Polytechnique de Paris (Route de Saclay, 91120 Palaiseau Cedex, France - France)","TSP - RS2M - D\u00e9partement R\u00e9seaux et Services Multim\u00e9dia Mobiles (T\u00e9l\u00e9com SudParis - 9 rue Charles Fourier - 91011 \u00c9vry cedex - France)"],"affiliations":[{"raw_affiliation_string":"SAMOVAR, T\u00e9l\u00e9com SudParis, Institut Polytechnique de Paris, Palaiseau, 91120, France","institution_ids":["https://openalex.org/I4210145102"]},{"raw_affiliation_string":"IP Paris - Institut Polytechnique de Paris (Route de Saclay, 91120 Palaiseau Cedex, France - France)","institution_ids":["https://openalex.org/I4210145102"]},{"raw_affiliation_string":"TSP - RS2M - D\u00e9partement R\u00e9seaux et Services Multim\u00e9dia Mobiles (T\u00e9l\u00e9com SudParis - 9 rue Charles Fourier - 91011 \u00c9vry cedex - France)","institution_ids":["https://openalex.org/I4210145102","https://openalex.org/I4387153010"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014176390","display_name":"Reza Farahbakhsh","orcid":"https://orcid.org/0000-0003-3219-3700"},"institutions":[{"id":"https://openalex.org/I4210145102","display_name":"Institut Polytechnique de Paris","ror":"https://ror.org/042tfbd02","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210145102"]},{"id":"https://openalex.org/I4387153010","display_name":"T\u00e9l\u00e9com SudParis","ror":"https://ror.org/05xvk4r52","country_code":"FR","type":"education","lineage":["https://openalex.org/I205703379","https://openalex.org/I4210145102","https://openalex.org/I4387153010"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Reza Farahbakhsh","raw_affiliation_strings":["SAMOVAR, T\u00e9l\u00e9com SudParis, Institut Polytechnique de Paris, Palaiseau, 91120, France","IP Paris - Institut Polytechnique de Paris (Route de Saclay, 91120 Palaiseau Cedex, France - France)","TSP - RS2M - D\u00e9partement R\u00e9seaux et Services Multim\u00e9dia Mobiles (T\u00e9l\u00e9com SudParis - 9 rue Charles Fourier - 91011 \u00c9vry cedex - France)"],"affiliations":[{"raw_affiliation_string":"SAMOVAR, T\u00e9l\u00e9com SudParis, Institut Polytechnique de Paris, Palaiseau, 91120, France","institution_ids":["https://openalex.org/I4210145102"]},{"raw_affiliation_string":"IP Paris - Institut Polytechnique de Paris (Route de Saclay, 91120 Palaiseau Cedex, France - France)","institution_ids":["https://openalex.org/I4210145102"]},{"raw_affiliation_string":"TSP - RS2M - D\u00e9partement R\u00e9seaux et Services Multim\u00e9dia Mobiles (T\u00e9l\u00e9com SudParis - 9 rue Charles Fourier - 91011 \u00c9vry cedex - France)","institution_ids":["https://openalex.org/I4210145102","https://openalex.org/I4387153010"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5107205316","display_name":"No\u00ebl Crespi","orcid":"https://orcid.org/0000-0003-2962-192X"},"institutions":[{"id":"https://openalex.org/I4210145102","display_name":"Institut Polytechnique de Paris","ror":"https://ror.org/042tfbd02","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210145102"]},{"id":"https://openalex.org/I4387153010","display_name":"T\u00e9l\u00e9com SudParis","ror":"https://ror.org/05xvk4r52","country_code":"FR","type":"education","lineage":["https://openalex.org/I205703379","https://openalex.org/I4210145102","https://openalex.org/I4387153010"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Noel Crespi","raw_affiliation_strings":["SAMOVAR, T\u00e9l\u00e9com SudParis, Institut Polytechnique de Paris, Palaiseau, 91120, France","IP Paris - Institut Polytechnique de Paris (Route de Saclay, 91120 Palaiseau Cedex, France - France)","TSP - RS2M - D\u00e9partement R\u00e9seaux et Services Multim\u00e9dia Mobiles (T\u00e9l\u00e9com SudParis - 9 rue Charles Fourier - 91011 \u00c9vry cedex - France)"],"affiliations":[{"raw_affiliation_string":"SAMOVAR, T\u00e9l\u00e9com SudParis, Institut Polytechnique de Paris, Palaiseau, 91120, France","institution_ids":["https://openalex.org/I4210145102"]},{"raw_affiliation_string":"IP Paris - Institut Polytechnique de Paris (Route de Saclay, 91120 Palaiseau Cedex, France - France)","institution_ids":["https://openalex.org/I4210145102"]},{"raw_affiliation_string":"TSP - RS2M - D\u00e9partement R\u00e9seaux et Services Multim\u00e9dia Mobiles (T\u00e9l\u00e9com SudParis - 9 rue Charles Fourier - 91011 \u00c9vry cedex - France)","institution_ids":["https://openalex.org/I4210145102","https://openalex.org/I4387153010"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5094038606"],"corresponding_institution_ids":["https://openalex.org/I4210145102","https://openalex.org/I4387153010"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":{"value":2390,"currency":"EUR","value_usd":2990},"fwci":11.6476,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.98169603,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":"15","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11147","display_name":"Misinformation and Its Impacts","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T11147","display_name":"Misinformation and Its Impacts","score":1.0,"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"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9890000224113464,"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":0.9876000285148621,"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/scarcity","display_name":"Scarcity","score":0.7576404809951782},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6551845073699951},{"id":"https://openalex.org/keywords/fake-news","display_name":"Fake news","score":0.5843096375465393},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.4540891647338867},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.33872130513191223},{"id":"https://openalex.org/keywords/internet-privacy","display_name":"Internet privacy","score":0.3301442265510559},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.07630103826522827}],"concepts":[{"id":"https://openalex.org/C109747225","wikidata":"https://www.wikidata.org/wiki/Q815758","display_name":"Scarcity","level":2,"score":0.7576404809951782},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6551845073699951},{"id":"https://openalex.org/C2779756789","wikidata":"https://www.wikidata.org/wiki/Q28549308","display_name":"Fake news","level":2,"score":0.5843096375465393},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.4540891647338867},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.33872130513191223},{"id":"https://openalex.org/C108827166","wikidata":"https://www.wikidata.org/wiki/Q175975","display_name":"Internet privacy","level":1,"score":0.3301442265510559},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.07630103826522827},{"id":"https://openalex.org/C175444787","wikidata":"https://www.wikidata.org/wiki/Q39072","display_name":"Microeconomics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s13278-025-01505-z","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s13278-025-01505-z","pdf_url":"https://link.springer.com/content/pdf/10.1007/s13278-025-01505-z.pdf","source":{"id":"https://openalex.org/S2764891196","display_name":"Social Network Analysis and Mining","issn_l":"1869-5450","issn":["1869-5450","1869-5469"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Social Network Analysis and Mining","raw_type":"journal-article"},{"id":"pmh:oai:HAL:hal-05228033v1","is_oa":false,"landing_page_url":"https://hal.science/hal-05228033","pdf_url":null,"source":{"id":"https://openalex.org/S4406922466","display_name":"SPIRE - Sciences Po Institutional REpository","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Social Network Analysis and Mining, 2025, 15 (92), pp.1-16. ⟨10.1007/s13278-025-01505-z⟩","raw_type":"Journal articles"}],"best_oa_location":{"id":"doi:10.1007/s13278-025-01505-z","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s13278-025-01505-z","pdf_url":"https://link.springer.com/content/pdf/10.1007/s13278-025-01505-z.pdf","source":{"id":"https://openalex.org/S2764891196","display_name":"Social Network Analysis and Mining","issn_l":"1869-5450","issn":["1869-5450","1869-5469"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Social Network Analysis and Mining","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4413772162.pdf","grobid_xml":"https://content.openalex.org/works/W4413772162.grobid-xml"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W2582561810","https://openalex.org/W2913649461","https://openalex.org/W2970641574","https://openalex.org/W2979826702","https://openalex.org/W3021621101","https://openalex.org/W3034942609","https://openalex.org/W3139464810","https://openalex.org/W3164954869","https://openalex.org/W3171059312","https://openalex.org/W3176457774","https://openalex.org/W3180181113","https://openalex.org/W3185341429","https://openalex.org/W3205958211","https://openalex.org/W4205145976","https://openalex.org/W4293027464","https://openalex.org/W4309674289","https://openalex.org/W4320913149","https://openalex.org/W4367046686","https://openalex.org/W4386693657","https://openalex.org/W4386913943","https://openalex.org/W4388524030","https://openalex.org/W4388834782","https://openalex.org/W4389513437","https://openalex.org/W4391215636","https://openalex.org/W4392173902","https://openalex.org/W4392325552","https://openalex.org/W4393001808","https://openalex.org/W4393160654","https://openalex.org/W4399205453","https://openalex.org/W4399386433","https://openalex.org/W4400108903","https://openalex.org/W4401070260","https://openalex.org/W4402670893","https://openalex.org/W4404173792","https://openalex.org/W6949549905"],"related_works":["https://openalex.org/W1571141552","https://openalex.org/W4391636338","https://openalex.org/W4386067343","https://openalex.org/W4294250823","https://openalex.org/W2093086151","https://openalex.org/W55936454","https://openalex.org/W2095572632","https://openalex.org/W2944249426","https://openalex.org/W4294609170","https://openalex.org/W129955550"],"abstract_inverted_index":{"The":[0,157],"rise":[1],"in":[2,14,170],"online":[3],"news":[4,34,84,94,139,206],"consumption,":[5],"especially":[6],"during":[7],"critical":[8],"events,":[9],"coupled":[10],"with":[11,150],"rapid":[12],"advances":[13],"generative":[15],"artificial":[16],"intelligence":[17],"(AI),":[18],"has":[19],"accelerated":[20],"the":[21,26,38,98,137,146,182,194],"spread":[22],"of":[23,42,100,165,196],"misinformation,":[24],"underscoring":[25],"urgent":[27],"need":[28],"for":[29,69],"fast":[30],"and":[31,40,52,88,119],"effective":[32],"fake":[33,93,138,205],"detection":[35,54,101],"approaches.":[36],"However,":[37],"scarcity":[39],"imbalance":[41],"high-quality":[43],"labeled":[44],"datasets":[45,95],"pose":[46],"significant":[47],"challenges":[48],"to":[49,81,96,161,167,181,203],"training":[50],"accurate":[51],"reliable":[53],"models.":[55,102],"In":[56],"this":[57,61],"study,":[58],"we":[59,77,107],"tackle":[60],"issue":[62],"by":[63],"leveraging":[64],"Large":[65],"Language":[66],"Models":[67],"(LLMs)":[68],"data":[70,198],"augmentation.":[71,121],"Expanding":[72],"upon":[73],"our":[74],"prior":[75],"work,":[76],"employ":[78],"Llama":[79],"3":[80],"generate":[82],"synthetic":[83],"samples":[85,176],"under":[86],"zero-shot":[87],"few-shot":[89],"settings,":[90],"enriching":[91],"existing":[92],"improve":[97],"performance":[99],"To":[103],"optimize":[104],"augmentation":[105,113,158],"effectiveness,":[106],"explore":[108],"several":[109],"strategies,":[110],"including":[111],"varying":[112],"rates,":[114],"random":[115,155],"versus":[116],"similarity-based":[117,151],"subsampling,":[118],"class-specific":[120],"Our":[122],"experiments,":[123],"using":[124],"BERT-based":[125],"classifiers":[126],"on":[127,187],"two":[128],"real-world":[129],"multilingual":[130],"datasets,":[131],"reveal":[132],"that":[133],"selectively":[134],"augmenting":[135],"only":[136],"class":[140],"at":[141],"lower":[142],"rates":[143],"typically":[144],"yields":[145],"most":[147],"consistent":[148],"improvements,":[149],"subsampling":[152],"slightly":[153],"outperforming":[154],"selection.":[156],"approach":[159],"led":[160],"F1":[162],"score":[163],"improvements":[164],"up":[166],"7.7":[168],"points":[169],"some":[171],"languages.":[172],"Additionally,":[173],"while":[174],"few-shot-generated":[175],"generally":[177],"exhibit":[178],"greater":[179],"similarity":[180],"original":[183],"ones,":[184],"their":[185],"impact":[186],"classification":[188],"remains":[189],"inconsistent.":[190],"These":[191],"findings":[192],"highlight":[193],"potential":[195],"LLM-driven":[197],"augmentation,":[199],"when":[200],"carefully":[201],"tuned,":[202],"enhance":[204],"detection.":[207]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-15T08:11:43.952461","created_date":"2025-10-10T00:00:00"}