{"id":"W4297475198","doi":"10.1186/s12859-022-04933-2","title":"Identifying health related occupations of Twitter users through word embedding and deep neural networks","year":2022,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Social Media in Health Education","field":"Social Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Brandon University; Lakehead University","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada; Lakehead University","keywords":"Computer science; Word embedding; Artificial neural network; Embedding; Artificial intelligence; Word (group theory); Encoder; Recurrent neural network; Transformer; Deep learning; Recall; Social media; Construct (python library); Machine learning; Precision and recall; F1 score; Natural language processing; Information retrieval; World Wide Web","routes":{"ca_aff":true,"ca_fund":true,"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":["sts"],"consensus_categories":[],"category_scores_codex":[0.001111915,0.00008013161,0.0001763632,0.0000935969,0.001368274,0.00005036369,0.0001631738,0.00006391985,0.0001210107],"category_scores_gemma":[0.000811332,0.00009183985,0.00004178671,0.0007041752,0.0001342306,0.0004522832,0.00008683292,0.0002582787,0.000003584136],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002966387,"about_ca_system_score_gemma":0.0003130726,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002177997,"about_ca_topic_score_gemma":0.0005615272,"domain_scores_codex":[0.9982646,0.0002749751,0.0006388529,0.00008980713,0.0003922284,0.0003395823],"domain_scores_gemma":[0.9982088,0.0009426047,0.0005383529,0.0001366818,0.00006127619,0.0001122481],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001761232,0.00004892658,0.1089166,0.0002836583,0.00001820845,2.999599e-7,0.8450479,0.01622631,3.199789e-7,0.004938613,0.001426953,0.02307467],"study_design_scores_gemma":[0.0003321706,0.00006817417,0.02903396,0.00004507146,0.00002287688,0.000003816796,0.2735745,0.6915546,6.506815e-7,0.001002418,0.004159241,0.0002025414],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.865327,0.001849074,0.1046794,0.006123438,0.01510419,0.004059091,0.00002966134,0.0003197738,0.002508388],"genre_scores_gemma":[0.9058616,0.0002714257,0.09218086,0.001027008,0.0002559568,0.0002788592,0.00007204514,0.00002033191,0.00003191121],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6753283,"threshold_uncertainty_score":0.9999318,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1478485987947585,"score_gpt":0.4160680910723472,"score_spread":0.2682194922775887,"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."}}