{"id":"https://openalex.org/W4281477720","doi":"https://doi.org/10.48550/arxiv.2205.07154","title":"Evaluating Generalizability of Fine-Tuned Models for Fake News Detection","display_name":"Evaluating Generalizability of Fine-Tuned Models for Fake News Detection","publication_year":2022,"publication_date":"2022-05-15","ids":{"openalex":"https://openalex.org/W4281477720","doi":"https://doi.org/10.48550/arxiv.2205.07154"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2205.07154","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2205.07154","pdf_url":"https://arxiv.org/pdf/2205.07154","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2205.07154","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5043704066","display_name":"Abhijit Suprem","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Suprem, Abhijit","raw_affiliation_strings":["Georgia Institute of Technology Atlanta , GA , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology Atlanta , GA , USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081442372","display_name":"Calton Pu","orcid":"https://orcid.org/0000-0002-6616-8987","observed_orcids":["https://orcid.org/0000-0002-6616-8987"]},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pu, Calton","raw_affiliation_strings":["Georgia Institute of Technology Atlanta , GA , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology Atlanta , GA , USA","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I130701444"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":8,"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/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/T11644","display_name":"Spam and Phishing Detection","score":0.0,"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/T10028","display_name":"Topic Modeling","score":0.0,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/fake-news-detection","display_name":"fake news detection","score":0.9990000128746033},{"id":"https://openalex.org/keywords/generalizability","display_name":"generalizability","score":0.7990000247955322},{"id":"https://openalex.org/keywords/concept-drift","display_name":"concept drift","score":0.8849999904632568},{"id":"https://openalex.org/keywords/overfitting","display_name":"overfitting","score":0.7300000190734863},{"id":"https://openalex.org/keywords/fine-tuned-models","display_name":"fine-tuned models","score":0.6700000166893005},{"id":"https://openalex.org/keywords/pre-trained-language-models","display_name":"pre-trained language models","score":0.8489999771118164},{"id":"https://openalex.org/keywords/covid-19-misinformation","display_name":"COVID-19 misinformation","score":0.8569999933242798},{"id":"https://openalex.org/keywords/infodemic","display_name":"infodemic","score":0.9350000023841858},{"id":"https://openalex.org/keywords/unseen-data","display_name":"unseen data","score":0.7080000042915344},{"id":"https://openalex.org/keywords/k-means-clustering","display_name":"K-means clustering","score":0.9340000152587891}],"concepts":[{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.9351215362548828},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.7872499227523804},{"id":"https://openalex.org/C2776990098","wikidata":"https://www.wikidata.org/wiki/Q13579947","display_name":"Misinformation","level":2,"score":0.7507874369621277},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6852315664291382},{"id":"https://openalex.org/C2780148112","wikidata":"https://www.wikidata.org/wiki/Q1432581","display_name":"Proxy (statistics)","level":2,"score":0.6804484724998474},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5608399510383606},{"id":"https://openalex.org/C207968372","wikidata":"https://www.wikidata.org/wiki/Q310401","display_name":"k-means clustering","level":3,"score":0.4373360276222229},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3784433901309967},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3346208930015564},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3232574462890625},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.18771305680274963},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10545423626899719},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.10412678122520447},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.08424687385559082}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2205.07154","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2205.07154","pdf_url":"https://arxiv.org/pdf/2205.07154","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2205.07154","doi":"https://doi.org/10.48550/arxiv.2205.07154","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2205.07154","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2205.07154","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2205.07154","pdf_url":"https://arxiv.org/pdf/2205.07154","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4281477720.pdf","grobid_xml":"https://content.openalex.org/works/W4281477720.grobid-xml"},"referenced_works_count":18,"referenced_works":["https://openalex.org/W1505456515","https://openalex.org/W2346439649","https://openalex.org/W2896457183","https://openalex.org/W2975059944","https://openalex.org/W2989195139","https://openalex.org/W2992787485","https://openalex.org/W3008258803","https://openalex.org/W3022717752","https://openalex.org/W3032089915","https://openalex.org/W3046340454","https://openalex.org/W3081751010","https://openalex.org/W3134304069","https://openalex.org/W3183516990","https://openalex.org/W3195577433","https://openalex.org/W4221162054","https://openalex.org/W4323644147","https://openalex.org/W4324392584","https://openalex.org/W6903717247"],"related_works":["https://openalex.org/W4280643589","https://openalex.org/W3157206169","https://openalex.org/W4281387393","https://openalex.org/W4414560456","https://openalex.org/W4375929029","https://openalex.org/W4394789421","https://openalex.org/W3156140734","https://openalex.org/W4391880986","https://openalex.org/W3214007012","https://openalex.org/W3158073235"],"abstract_inverted_index":{"The":[0],"Covid-19":[1,25],"pandemic":[2],"has":[3],"caused":[4],"a":[5,118],"dramatic":[6],"and":[7,19,66,87,120],"parallel":[8],"rise":[9],"in":[10,162],"dangerous":[11],"misinformation,":[12],"denoted":[13],"an":[14],"`infodemic'":[15],"by":[16,144],"the":[17,24,164],"CDC":[18],"WHO.":[20],"Misinformation":[21],"tied":[22],"to":[23,32,39,50,159],"infodemic":[26],"changes":[27],"continuously;":[28],"this":[29,59,112],"can":[30,43],"lead":[31],"performance":[33,90],"degradation":[34],"of":[35,55,64,98,133],"fine-tuned":[36,67],"models":[37,47,80,106],"due":[38],"concept":[40],"drift.":[41],"Degredation":[42],"be":[44],"mitigated":[45],"if":[46],"generalize":[48],"well-enough":[49],"capture":[51],"some":[52,96],"cyclical":[53],"aspects":[54],"drifted":[56],"data.":[57,93,135],"In":[58],"paper,":[60],"we":[61,114],"explore":[62],"generalizability":[63,138,153],"pre-trained":[65],"fake":[68,73,141,165],"news":[69,74,142,166],"detectors":[70],"across":[71,147],"9":[72],"datasets.":[75,148],"We":[76,149],"show":[77],"that":[78,101],"existing":[79],"often":[81],"overfit":[82],"on":[83,91,95,111,124,139],"their":[84],"training":[85,104],"dataset":[86],"have":[88,107],"poor":[89],"unseen":[92,99,134,140],"However,":[94],"subsets":[97,132],"data":[100],"overlap":[102],"with":[103],"data,":[105],"higher":[108],"accuracy.":[109],"Based":[110],"observation,":[113],"also":[115],"present":[116,150],"KMeans-Proxy,":[117],"fast":[119],"effective":[121],"method":[122],"based":[123],"K-Means":[125],"clustering":[126],"for":[127],"quickly":[128],"identifying":[129],"these":[130],"overlapping":[131],"KMeans-Proxy":[136,158],"improves":[137],"datasets":[143],"0.1-0.2":[145],"f1-points":[146],"both":[151],"our":[152],"experiments":[154],"as":[155,157],"well":[156],"further":[160],"research":[161],"tackling":[163],"problem.":[167]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2022-05-26T00:00:00"}