{"id":"W4389086927","doi":"10.2196/50379","title":"Generating Contextual Variables From Web-Based Data for Health Research: Tutorial on Web Scraping, Text Mining, and Spatial Overlay Analysis","year":2023,"lang":"en","type":"article","venue":"JMIR Public Health and Surveillance","topic":"Data-Driven Disease Surveillance","field":"Medicine","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"Wilfrid Laurier University; St. Michael's Hospital; Public Health Ontario; University of Toronto","funders":"","keywords":"Computer science; Preprint; Python (programming language); Data mining; World Wide Web; Data science; Information retrieval","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.009282221,0.0003510034,0.001259298,0.0008159977,0.0007976015,0.0003103118,0.0004005545,0.0001680452,0.00008520763],"category_scores_gemma":[0.005510891,0.000325632,0.0001027394,0.001810676,0.0002591111,0.0002066708,0.0003121812,0.0003791257,0.00001327293],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002126433,"about_ca_system_score_gemma":0.005386352,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002329845,"about_ca_topic_score_gemma":0.01130418,"domain_scores_codex":[0.9936177,0.001436881,0.0009427561,0.001497541,0.001019108,0.001486043],"domain_scores_gemma":[0.9930552,0.002865428,0.0003921966,0.00153973,0.0003843673,0.001763044],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001210316,0.0002825567,0.396272,0.0007309879,0.0005008782,0.00002345295,0.0004528596,0.0000330339,0.0001120837,0.0001387327,0.4907216,0.1095215],"study_design_scores_gemma":[0.005995683,0.001000756,0.1552695,0.00009808266,0.000008737066,0.000002144257,0.0003049984,0.2493451,5.859542e-7,0.000009598165,0.5876498,0.0003149977],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9016479,0.003527372,0.002053157,0.05693625,0.001226844,0.003175693,0.03016462,0.0008383007,0.0004298597],"genre_scores_gemma":[0.9610037,0.0007021217,0.001922599,0.008119543,0.002005037,0.0002916889,0.02558305,0.00007603292,0.0002961872],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2493121,"threshold_uncertainty_score":0.9999196,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1651010824464325,"score_gpt":0.4149373977121152,"score_spread":0.2498363152656827,"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."}}