{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004604729,0.00104177,0.0003636691,0.001484847,0.0002276264,0.0005461643,0.0004168913,0.0007246776,0.001294237],"category_scores_gemma":[0.001887082,0.0001892312,0.0004875585,0.0009914072,0.0002202434,0.001053763,0.0005920296,0.0006676768,0.0008643055],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005196765,"about_ca_system_score_gemma":0.0002982862,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00743475,"about_ca_topic_score_gemma":0.01268105,"domain_scores_codex":[0.9996576,0.00009780755,0.00003297017,0.00009587737,0.00006204245,0.00005353925],"domain_scores_gemma":[0.9991655,0.0004093635,0.0001492773,0.00008259959,0.0001507701,0.00004252827],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001096271,0.001243986,0.07797335,0.000476303,0.000307411,0.0004962263,0.0004419628,0.1027659,0.01877803,0.001168414,0.01124835,0.7840039],"study_design_scores_gemma":[0.00001185183,0.0001174195,0.01143113,0.00002860852,0.00003421612,0.00008416455,0.0001471741,0.9797707,0.005917305,0.001595683,0.0008442739,0.00001743755],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8480353,0.001802577,0.1341178,0.00134428,0.0002899013,0.000176519,0.004850935,0.003297895,0.00608483],"genre_scores_gemma":[0.9469604,0.0004177654,0.04416155,0.0001385784,0.00008626119,0.00008063202,0.004392656,0.00003203181,0.003730215],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.00743475,"threshold_uncertainty_score":0.01478297,"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."}}