{"id":"W4401063616","doi":"10.1007/s11257-024-09413-1","title":"A deep neural network approach for fake news detection using linguistic and psychological features","year":2024,"lang":"en","type":"article","venue":"User Modeling and User-Adapted Interaction","topic":"Misinformation and Its Impacts","field":"Social Sciences","cited_by":6,"is_retracted":false,"has_abstract":false,"ca_institutions":"Vector Institute; Toronto Metropolitan University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Fake news; Baseline (sea); Feature (linguistics); Artificial intelligence; Multilayer perceptron; Artificial neural network; Social media; Machine learning; Natural language processing; Deep learning; Information retrieval; World Wide Web; Linguistics; Internet privacy","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":[0.000322608,0.0001303974,0.0001308639,0.00011089,0.0005569375,0.0005321523,0.00005147735,0.000155199,0.000012544],"category_scores_gemma":[0.0002378424,0.0001130644,0.00005319793,0.0001779755,0.0000357232,0.00052926,0.00001703804,0.000250086,0.000001354225],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006528875,"about_ca_system_score_gemma":0.00001778247,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006956117,"about_ca_topic_score_gemma":0.0004565757,"domain_scores_codex":[0.9990412,0.00007265244,0.0002255857,0.0002530211,0.0001500009,0.0002575358],"domain_scores_gemma":[0.9995617,0.00009657051,0.00005522955,0.00007661043,0.00009210414,0.0001177949],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0006472713,0.0001335401,0.0001454207,0.0002259596,0.0001106112,0.000003593657,0.0546832,0.7487481,0.0004963916,0.009524161,0.0008770609,0.1844046],"study_design_scores_gemma":[0.0001677343,0.00008116044,0.0000653146,0.00006061411,0.0000390188,0.00002234079,0.004637911,0.9884169,0.000006754476,0.0004896821,0.005876227,0.0001364125],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5195969,0.0004936044,0.4764263,0.0001336518,0.001026383,0.0002777112,0.000001877776,0.0001786035,0.001864961],"genre_scores_gemma":[0.9925789,0.0001801174,0.005984682,0.0002227215,0.0008217152,0.000006891408,0.00001234932,0.00001458005,0.0001780055],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.472982,"threshold_uncertainty_score":0.5131557,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1037651716012417,"score_gpt":0.3768437529848514,"score_spread":0.2730785813836096,"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."}}