{"id":"W2945267390","doi":"10.1177/2053951719843310","title":"Big Data and quality data for fake news and misinformation detection","year":2019,"lang":"en","type":"article","venue":"Big Data & Society","topic":"Misinformation and Its Impacts","field":"Social Sciences","cited_by":155,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada; Simon Fraser University; Nvidia","keywords":"Misinformation; Computer science; Variety (cybernetics); Data science; Quality (philosophy); Fake news; Perspective (graphical); Big data; Appeal; Data quality; Internet privacy; Data mining; Artificial intelligence; Computer security","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":[0.003170059,0.000108562,0.0001539325,0.00002171576,0.0005116636,0.000445662,0.001096587,0.0001368307,0.00002372758],"category_scores_gemma":[0.0008642844,0.00009937067,0.00001976394,0.0001745211,0.0001306624,0.00430266,0.001153724,0.0001005329,0.00002761519],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003663929,"about_ca_system_score_gemma":0.0001920336,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002327349,"about_ca_topic_score_gemma":0.005637088,"domain_scores_codex":[0.9986265,0.00007228921,0.000327734,0.0003663011,0.0003540269,0.0002531423],"domain_scores_gemma":[0.9973335,0.000187331,0.0002146326,0.002049546,0.00006817257,0.0001468165],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00002543775,0.00002157943,0.0007328371,0.0001674476,0.00003757226,2.183286e-8,0.02323442,3.122001e-7,0.0002077454,0.0004758393,0.1271338,0.847963],"study_design_scores_gemma":[0.0007538451,0.0000220333,0.006611254,0.00001724614,0.00002712438,9.12451e-7,0.0373719,0.01038929,0.00003679634,0.0000697597,0.9445081,0.0001917235],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.835719,0.001552819,0.09256361,0.007669263,0.004514758,0.003868583,0.03965477,0.0004440104,0.01401313],"genre_scores_gemma":[0.959827,0.004319161,0.003365617,0.002857504,0.00128421,0.000003208938,0.02707639,0.0000192391,0.001247645],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8477713,"threshold_uncertainty_score":0.4297529,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.356022604373388,"score_gpt":0.4058609883183898,"score_spread":0.04983838394500184,"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."}}