{"id":"W7066035670","doi":"","title":"False Positives: Opportunities and Dangers in Big Text Analysis","year":2012,"lang":"en","type":"other","venue":"KU ScholarWorks (The University of Kansas)","topic":"Historical and Linguistic Studies","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Big data; Digital humanities; Data collection; Information technology; Field (mathematics); Digital forensics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.1033147,0.001049896,0.001375434,0.0105664,0.005827265,0.01467646,0.002849742,0.006835638,0.005591762],"category_scores_gemma":[0.4142039,0.0014412,0.0008742223,0.008189889,0.01192981,0.02284262,0.00753846,0.008778321,0.002633709],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001747601,"about_ca_system_score_gemma":0.002514426,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00161514,"about_ca_topic_score_gemma":0.002984774,"domain_scores_codex":[0.8796886,0.07397985,0.005699729,0.007308539,0.03223336,0.001089946],"domain_scores_gemma":[0.3043211,0.6240648,0.02202087,0.02521705,0.02188572,0.002490468],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000533657,0.0001076127,0.04821564,0.002147784,0.0003606194,0.003152412,0.02063983,0.002073644,0.001245822,0.139598,0.2222332,0.5596917],"study_design_scores_gemma":[0.00008429339,0.0001221725,0.01359972,0.004223246,0.0002308134,0.006456283,0.01426161,0.021764,0.003901471,0.781809,0.1533,0.0002474],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.06089751,0.07072584,0.2726592,0.5369033,0.009498798,0.0005408699,0.002733888,0.003163121,0.04287741],"genre_scores_gemma":[0.6606306,0.02652246,0.1947107,0.08207418,0.01690944,0.0008400537,0.002276977,0.001626411,0.01440929],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.1033147,"threshold_uncertainty_score":0.546387,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03779193104012701,"score_gpt":0.2470813842919597,"score_spread":0.2092894532518327,"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."}}