{"id":"W3177364780","doi":"10.1186/s40708-021-00134-4","title":"A deep neural network approach for sentiment analysis of medically related texts: an analysis of tweets related to concussions in sports","year":2021,"lang":"en","type":"article","venue":"Brain Informatics","topic":"Traumatic Brain Injury Research","field":"Medicine","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; St. Michael's Hospital; Toronto Metropolitan University","funders":"Ontario Research Foundation","keywords":"Concussion; Context (archaeology); Convolutional neural network; Psychology; Sentiment analysis; Artificial intelligence; Injury prevention; Poison control; Computer science; Machine learning; Computer security; Applied psychology; Medicine; Medical emergency; History","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":[],"consensus_categories":[],"category_scores_codex":[0.002309048,0.0002279592,0.001525102,0.00181639,0.00006034179,0.00002016095,0.0002570036,0.0002773301,0.0005140544],"category_scores_gemma":[0.001603045,0.0001937689,0.0005507439,0.01056592,0.0001638602,0.0001661437,0.0001433563,0.0003519485,0.000001983037],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001254798,"about_ca_system_score_gemma":0.0002852684,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003084189,"about_ca_topic_score_gemma":0.00007149618,"domain_scores_codex":[0.9952747,0.0001890229,0.00262305,0.0002574221,0.001129355,0.0005264269],"domain_scores_gemma":[0.9967362,0.0008133126,0.0005714265,0.0009409164,0.000501334,0.0004367619],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0006586634,0.001817279,0.2391208,0.001139716,0.02368171,0.00007755869,0.0422378,0.6633689,0.0003068307,0.002020063,0.002678112,0.02289252],"study_design_scores_gemma":[0.001508448,0.000226775,0.1795566,0.0001109477,0.005029536,0.00001197311,0.004383488,0.808783,0.00004543017,0.00007060101,0.0001193389,0.0001538885],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9779259,0.00007182841,0.01667682,0.001117831,0.00007645682,0.001270908,0.00007746324,0.00005006766,0.002732745],"genre_scores_gemma":[0.9471011,0.000008688206,0.05001009,0.0006566006,0.00001227808,0.00004672433,0.001742094,0.00002445067,0.0003979855],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.145414,"threshold_uncertainty_score":0.7901667,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02914208344683134,"score_gpt":0.3393988212311144,"score_spread":0.310256737784283,"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."}}