{"id":"W6976853247","doi":"10.6084/m9.figshare.26617876","title":"Additional file 1 of Empowering health geography research with location-based social media data: innovative food word expansion and energy density prediction via word embedding and machine learning","year":2024,"lang":"en","type":"article","venue":"Open MIND","topic":"Data-Driven Disease Surveillance","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Word (group theory); Calibration; Mixture model; Social media; Embedding; Vertical axis; Value (mathematics); Gaussian","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001668024,0.0008673102,0.0007873246,0.001454032,0.0007435873,0.001542718,0.001703399,0.001084999,0.8279667],"category_scores_gemma":[0.03437937,0.0004529881,0.0006038366,0.002958465,0.0002607748,0.00131165,0.001136718,0.001049246,0.1596594],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009517799,"about_ca_system_score_gemma":0.001840741,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01298653,"about_ca_topic_score_gemma":0.02862999,"domain_scores_codex":[0.9994845,0.000129174,0.00006794111,0.000139458,0.0001130694,0.00006583659],"domain_scores_gemma":[0.9836861,0.01314658,0.0005360409,0.0009645458,0.001285369,0.0003813948],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001429464,0.00005817586,0.002403481,0.0009010969,0.00002378154,0.0000481996,0.00006627123,0.0008948894,0.00005871198,0.0008625318,0.9848541,0.009685843],"study_design_scores_gemma":[0.005739201,0.0003546296,0.04071187,0.002707214,0.0002259867,0.0004932379,0.001281,0.01508256,0.001832605,0.02568677,0.9056628,0.0002222943],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.0001974275,0.000006856847,0.0004916426,0.00008704453,0.00001622674,0.0000551314,0.9982219,0.0002810226,0.0006426974],"genre_scores_gemma":[0.01344709,0.0000941045,0.009800646,0.0003364697,0.0000882305,0.002476439,0.9649835,0.001057457,0.007716153],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.8279667,"threshold_uncertainty_score":0.2453846,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07095707022725643,"score_gpt":0.3595208128628305,"score_spread":0.288563742635574,"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."}}