{"id":"W4410747314","doi":"10.1111/gean.70016","title":"Can Topic Modeling of Local Newspaper Texts Enhance Understanding of Neighborhood Effects on Health?","year":2025,"lang":"en","type":"article","venue":"Geographical Analysis","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Arts and Humanities Research Council; Department of Health and Social Care; National Institute for Health and Care Research; Canadian Institute of Steel Construction","keywords":"Newspaper; Computer science; Data science; Advertising; Business","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":[],"consensus_categories":[],"category_scores_codex":[0.0008441637,0.0001094333,0.0005432554,0.000904794,0.0002800859,0.0000185861,0.0002047604,0.00008620347,0.00006362981],"category_scores_gemma":[0.0001392977,0.00009729614,0.0005757679,0.005590873,0.0002159583,0.0000362869,0.00004020117,0.0001322029,5.588163e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008716681,"about_ca_system_score_gemma":0.0001516249,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007500905,"about_ca_topic_score_gemma":0.01110259,"domain_scores_codex":[0.9980572,0.0004715594,0.0004375018,0.0002921638,0.0004929081,0.0002486089],"domain_scores_gemma":[0.9986588,0.000758386,0.0001579729,0.0001899215,0.0001273568,0.0001075788],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00004971111,0.000258401,0.05488399,0.0001783204,0.002914667,0.000002174827,0.001914068,0.1197994,0.00004446259,0.6726367,0.00003601014,0.147282],"study_design_scores_gemma":[0.0005595654,0.0002010021,0.02726493,0.0002636641,0.002674451,8.375764e-8,0.004064008,0.3004738,0.0003439181,0.6635412,0.0002453241,0.000368018],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08619784,0.000626159,0.8966935,0.01048506,0.00007999177,0.0001235906,0.000004308049,0.00002736643,0.005762166],"genre_scores_gemma":[0.998333,0.0001991441,0.0009303592,0.0003773069,0.00003386303,0.000004775478,0.000007071231,0.000002980913,0.0001115336],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9121351,"threshold_uncertainty_score":0.9991083,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02365192138780933,"score_gpt":0.3520915653434699,"score_spread":0.3284396439556606,"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."}}