{"id":"W4386799916","doi":"10.1186/s12942-023-00344-5","title":"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":2023,"lang":"en","type":"article","venue":"International Journal of Health Geographics","topic":"Human Mobility and Location-Based Analysis","field":"Social Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"General Electric (Canada); University of Toronto","funders":"Connaught Fund","keywords":"Word embedding; Word (group theory); Context (archaeology); Computer science; Artificial intelligence; Social media; Natural language processing; Cluster analysis; Data science; Embedding; Geography; Mathematics; World Wide Web","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0103848,0.0001343954,0.0003097661,0.00191102,0.001934233,0.0001878078,0.0003839039,0.00009644155,0.00001132475],"category_scores_gemma":[0.0008210563,0.0001274954,0.00004809448,0.002994322,0.0005887947,0.0004513521,0.0001157605,0.0007094798,4.82569e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001932047,"about_ca_system_score_gemma":0.001340497,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.007595485,"about_ca_topic_score_gemma":0.03140195,"domain_scores_codex":[0.9957048,0.001181817,0.0007366129,0.0003384937,0.001643474,0.0003947554],"domain_scores_gemma":[0.9954303,0.001084383,0.0007023879,0.0001390652,0.00242363,0.0002202504],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0003927771,0.0002530794,0.5012138,0.000151842,0.0005148188,0.00001846044,0.03473713,0.002993164,0.00001348693,0.003813894,0.0004151828,0.4554824],"study_design_scores_gemma":[0.002834057,0.001276674,0.8575186,0.001251281,0.00006473102,0.00002610333,0.04286508,0.06949351,0.00001469262,0.00710094,0.01702736,0.0005269254],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8876668,0.002546242,0.07736482,0.03133302,0.0006370854,0.0002253955,0.00008475074,0.0001106202,0.0000312557],"genre_scores_gemma":[0.996044,0.002432866,0.0004382294,0.0003687515,0.0004297297,0.000006875714,0.000259501,0.00001433176,0.000005686205],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4549555,"threshold_uncertainty_score":0.9993651,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09347754292934168,"score_gpt":0.4107064066069726,"score_spread":0.3172288636776309,"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."}}