{"id":"W4210299703","doi":"10.1007/s41060-021-00302-z","title":"Fake news detection based on news content and social contexts: a transformer-based approach","year":2022,"lang":"en","type":"article","venue":"International Journal of Data Science and Analytics","topic":"Misinformation and Its Impacts","field":"Social Sciences","cited_by":270,"is_retracted":false,"has_abstract":false,"ca_institutions":"Toronto Metropolitan University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Unavailability; Computer science; Exploit; Fake news; Economic shortage; Social media; Encoder; Transformer; Artificial intelligence; Machine learning; Computer security; World Wide Web; Internet privacy; Engineering","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002143511,0.00006907052,0.0001167094,0.0003758343,0.0007654658,0.0003623049,0.0007544495,0.00002271603,0.00006200732],"category_scores_gemma":[0.0003667338,0.00005854648,0.00003662957,0.0003319968,0.0004142373,0.001477328,0.00005433677,0.0001861867,7.22212e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001906543,"about_ca_system_score_gemma":0.0008015288,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002485398,"about_ca_topic_score_gemma":0.0002050037,"domain_scores_codex":[0.9976373,0.00007025196,0.0003085533,0.0001371444,0.001691253,0.0001554893],"domain_scores_gemma":[0.9989906,0.00007514618,0.0002764025,0.00008934228,0.0004376649,0.0001308636],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001115593,0.0009687634,0.00331207,0.00003602164,0.0001616216,0.00003664343,0.03476288,0.003945223,0.003086017,0.01965899,0.006387776,0.9265284],"study_design_scores_gemma":[0.006539668,0.001170135,0.006882081,0.00007495422,0.0001301231,0.00008834786,0.1597462,0.4524367,0.0005961716,0.0005001681,0.3712617,0.0005737023],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6890208,0.0001860603,0.1862271,0.08586822,0.002730922,0.0007780161,0.001107243,0.00005926183,0.03402242],"genre_scores_gemma":[0.9959363,0.0000497071,0.0004260537,0.00337452,0.0001465234,5.051063e-7,0.00001694818,0.000002673917,0.00004680231],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9259547,"threshold_uncertainty_score":0.5887421,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1382122536767137,"score_gpt":0.3690256195116446,"score_spread":0.230813365834931,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}