{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0167734,0.001112508,0.001069969,0.01090142,0.002296669,0.004461017,0.001928006,0.003539966,0.00211627],"category_scores_gemma":[0.1070467,0.0007712425,0.0008891636,0.01101935,0.002152317,0.00862523,0.003211477,0.003300911,0.001400182],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002007736,"about_ca_system_score_gemma":0.001931526,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004153929,"about_ca_topic_score_gemma":0.005236608,"domain_scores_codex":[0.9775016,0.01099718,0.002294522,0.002089807,0.006424614,0.0006922678],"domain_scores_gemma":[0.8108038,0.09711405,0.02709384,0.04171576,0.0195175,0.003755118],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.001648057,0.001594883,0.4733126,0.004864557,0.0008212632,0.001159564,0.004763978,0.02981763,0.007306212,0.0328137,0.168855,0.2730425],"study_design_scores_gemma":[0.0002923611,0.0006169925,0.4243819,0.002108735,0.0005214724,0.002560846,0.00831086,0.2397972,0.02706782,0.08752641,0.2063491,0.000466228],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5844591,0.01369914,0.14774,0.04104204,0.002092645,0.001897385,0.1799392,0.005363944,0.02376653],"genre_scores_gemma":[0.7268105,0.002554846,0.1214091,0.001361041,0.001407842,0.001039923,0.1436641,0.0003781844,0.001374517],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0167734,"threshold_uncertainty_score":0.08870727,"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."}}