{"id":"W2489258484","doi":"10.1017/s0003055417000570","title":"Reading Between the Lines: Prediction of Political Violence Using Newspaper Text","year":2017,"lang":"en","type":"article","venue":"American Political Science Review","topic":"Political Conflict and Governance","field":"Social Sciences","cited_by":122,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Newspaper; Variation (astronomy); Context (archaeology); Reading (process); Armed conflict; Computer science; Politics; Political science; Data science; History; Law","routes":{"ca_aff":true,"ca_fund":false,"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":[0.001281449,0.000517097,0.0003874312,0.005766621,0.0002555122,0.001465194,0.0004222349,0.0006984929,0.00396789],"category_scores_gemma":[0.011867,0.0002024181,0.0003984082,0.004433904,0.0002339622,0.001761024,0.0005089583,0.0008099686,0.002027221],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000346036,"about_ca_system_score_gemma":0.0002037356,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002820799,"about_ca_topic_score_gemma":0.002646791,"domain_scores_codex":[0.999213,0.0003896315,0.00007413377,0.0001407296,0.000135968,0.00004662343],"domain_scores_gemma":[0.988203,0.008952599,0.001615281,0.0002305698,0.0006855305,0.000313029],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0008381819,0.0004463705,0.7110646,0.0009648896,0.0006916785,0.0006359353,0.001308292,0.01245528,0.001968294,0.002352919,0.01890309,0.2483704],"study_design_scores_gemma":[0.00008868843,0.000302213,0.8629104,0.0003922596,0.0004033663,0.0003620519,0.001709641,0.1049457,0.00215801,0.007540218,0.01911486,0.00007255533],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9352357,0.008778309,0.0188145,0.002062223,0.0003975682,0.0002264342,0.01733054,0.0004222057,0.0167326],"genre_scores_gemma":[0.9748963,0.002431858,0.006991833,0.0001187914,0.0006190411,0.000110315,0.01236957,0.00003207837,0.002430208],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.005766621,"threshold_uncertainty_score":0.01327389,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07314714434523127,"score_gpt":0.4176653248709075,"score_spread":0.3445181805256762,"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."}}