{"id":"W3110640267","doi":"10.5539/ijel.v11n1p99","title":"Linguistic-Based Detection of Fake News in Social Media","year":2020,"lang":"en","type":"article","venue":"International Journal of English Linguistics","topic":"Misinformation and Its Impacts","field":"Social Sciences","cited_by":60,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Social media; Test (biology); Filter (signal processing); Natural language processing; Fake news; Set (abstract data type); Linguistic analysis; Field (mathematics); Linguistics; Artificial intelligence; Information retrieval; World Wide Web; Internet privacy; Mathematics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0005288767,0.00006867365,0.0001691091,0.0001974716,0.00005366906,0.00005921843,0.0003278366,0.0000821049,0.0001036823],"category_scores_gemma":[0.3167157,0.00007037829,0.00009168842,0.0002118446,0.00008683846,0.00007071502,0.00001777851,0.0002346517,0.000003298466],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001154747,"about_ca_system_score_gemma":0.0004054907,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005551218,"about_ca_topic_score_gemma":0.0002658876,"domain_scores_codex":[0.9983234,0.0000773763,0.0006279872,0.000055304,0.0007950907,0.0001207903],"domain_scores_gemma":[0.9870429,0.000364668,0.0005654732,0.00003194935,0.01185966,0.0001353598],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001310626,0.0005044981,0.006386451,0.00008432702,0.0002099899,0.000122662,0.830793,0.003436134,0.0003398523,0.1065663,0.01476049,0.03548564],"study_design_scores_gemma":[0.001957488,0.0001156042,0.002915725,0.00008000685,0.00003027812,2.767939e-7,0.01515452,0.001020482,0.001922309,0.001598692,0.9750276,0.0001770406],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.2249968,0.0002195943,0.01081525,0.002123402,0.07583939,0.0003500103,0.0001507481,0.0001170755,0.6853878],"genre_scores_gemma":[0.9789129,0.00003007063,0.0005766573,0.0004533412,0.02000962,1.342192e-7,0.000003713475,0.000006255202,0.00000725168],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9602671,"threshold_uncertainty_score":0.6890399,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04093300493071868,"score_gpt":0.3304429687366355,"score_spread":0.2895099638059169,"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."}}