{"id":"W2911707388","doi":"10.3233/jem-180458","title":"The racial ‘digital divide’ in the predictive power of Google trends data for forecasting the unemployment rate","year":2018,"lang":"en","type":"article","venue":"Journal of Economic and Social Measurement","topic":"Data-Driven Disease Surveillance","field":"Medicine","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"Saint Mary's University","funders":"","keywords":"Predictive power; Unemployment; Unemployment rate; Sample (material); Big data; Time series; Power (physics); Econometrics; Computer science; Demographic economics; Economics; Data mining; Machine learning; Economic growth","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003746315,0.00009202582,0.0002523538,0.00003606328,0.0002322071,0.00006410404,0.0003407435,0.00002858248,0.00001174407],"category_scores_gemma":[0.0003624439,0.00004516824,0.0001002787,0.00004054911,0.0002436108,0.0001677003,0.00008711947,0.0001177059,9.487146e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000150324,"about_ca_system_score_gemma":0.0002294172,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008399657,"about_ca_topic_score_gemma":0.0001647097,"domain_scores_codex":[0.9988543,0.0001074956,0.0005116554,0.0001188459,0.0002410441,0.0001666063],"domain_scores_gemma":[0.9988226,0.0002412548,0.0004806406,0.0002329711,0.0001836705,0.00003889445],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.01927695,0.001551997,0.1263822,0.0001997731,0.005178308,0.00003670538,0.05174065,0.0001141408,0.000574322,0.003359274,0.3129326,0.4786531],"study_design_scores_gemma":[0.01547775,0.005047826,0.4730896,0.0004506604,0.001006331,0.00009209689,0.0210455,0.005284355,0.0002237862,0.005874644,0.4719269,0.0004805215],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9824049,0.0008491298,0.000422145,0.0119816,0.0008025123,0.000632625,0.0007200319,0.00000521794,0.002181779],"genre_scores_gemma":[0.9987573,0.00002239819,0.00001762707,0.0001903292,0.0009535978,0.000007937977,0.00001242507,0.000008338458,0.00003006561],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4781726,"threshold_uncertainty_score":0.1841908,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1287611306283128,"score_gpt":0.3250426082791293,"score_spread":0.1962814776508165,"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."}}