{"id":"W2949542275","doi":"10.1145/3292500.3330774","title":"Blending Noisy Social Media Signals with Traditional Movement Variables to Predict Forced Migration","year":2019,"lang":"en","type":"article","venue":"","topic":"Human Mobility and Location-Based Analysis","field":"Social Sciences","cited_by":25,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Social Sciences and Humanities Research Council of Canada; John D. and Catherine T. MacArthur Foundation; National Science Foundation","keywords":"Leverage (statistics); Computer science; Newspaper; Social media; Conversation; Big data; Data science; Movement (music); Variable (mathematics); Artificial intelligence; Machine learning; Econometrics; Data mining; Sociology; Mathematics; Media studies; World Wide Web","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000751623,0.00008543798,0.0001370685,0.0001011783,0.0004891638,0.00009463751,0.0001386419,0.00006162292,0.008278456],"category_scores_gemma":[0.0000782452,0.0000732191,0.0000601513,0.0003671689,0.00007005584,0.000210431,0.00000873453,0.0000585274,0.0001143947],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001610378,"about_ca_system_score_gemma":0.0002535753,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002907678,"about_ca_topic_score_gemma":0.03681904,"domain_scores_codex":[0.9986279,0.0001181349,0.0001862901,0.0002320064,0.0006199536,0.0002157434],"domain_scores_gemma":[0.9993013,0.000322873,0.00005740592,0.00008745136,0.0001233927,0.0001076347],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","study_design_scores_codex":[0.0001771306,0.0005617947,0.03140078,0.00006641001,0.0003738398,0.000002126941,0.1265144,0.01732196,0.009011454,0.7884526,0.01736047,0.008757131],"study_design_scores_gemma":[0.00826987,0.002127907,0.2108325,0.0005731832,0.001311625,0.000001111014,0.4056217,0.06996906,0.0194182,0.172856,0.1042635,0.004755313],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9063973,0.000006925527,0.03263059,0.007000142,0.0001626489,0.0006822672,0.00004746765,0.00013611,0.0529365],"genre_scores_gemma":[0.9961169,0.000002443329,0.000519923,0.0006751709,0.0004039859,0.0000540735,0.00009113245,0.000006047787,0.002130278],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6155965,"threshold_uncertainty_score":0.9926281,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02740439724584318,"score_gpt":0.2589286778079679,"score_spread":0.2315242805621247,"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."}}