{"id":"W2973837416","doi":"10.1145/3342558.3345404","title":"Impact of In-domain Vector Representations on the Classification of Disease-related Tweets","year":2019,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Guelph","funders":"","keywords":"Computer science; Word embedding; Artificial intelligence; Sentiment analysis; Word (group theory); Natural language processing; Domain (mathematical analysis); Task (project management); Convolutional neural network; Embedding; Initialization; Machine learning; Mathematics","routes":{"ca_aff":true,"ca_fund":false,"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":[0.0001605059,0.00004059312,0.0000686882,0.00006206751,0.00001098092,0.000008834319,0.0003038439,0.00001738489,0.00007860138],"category_scores_gemma":[0.00004244926,0.00002523872,0.00005320092,0.0002417968,0.00001554666,0.0001031044,0.00004143381,0.00004753709,0.00002236653],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000284768,"about_ca_system_score_gemma":0.00005770505,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001199148,"about_ca_topic_score_gemma":0.000005525379,"domain_scores_codex":[0.999391,0.00006254713,0.0001915055,0.0001425098,0.0001428138,0.00006963989],"domain_scores_gemma":[0.9991068,0.0001546162,0.00008294571,0.0005967109,0.00003443047,0.00002451195],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.00001734625,0.0001435463,0.2590959,0.00001014336,0.00002286302,5.638638e-7,0.001260381,0.01181094,0.02469389,0.701484,0.0001766984,0.00128376],"study_design_scores_gemma":[0.0001217716,0.00002989861,0.8163091,0.00001300873,0.000001073753,1.10821e-7,0.00003063193,0.1768437,0.000273213,0.006348758,0.000002106312,0.00002656743],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9703528,0.00000595236,0.02334711,0.0010599,0.0000555364,0.0001790719,0.000001340553,0.00001476896,0.004983474],"genre_scores_gemma":[0.9987232,9.331463e-7,0.00108234,0.00001408259,0.000003591244,0.000004182779,0.000001060618,0.000002134681,0.0001684582],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6951352,"threshold_uncertainty_score":0.1029205,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0348331680969018,"score_gpt":0.305411897964036,"score_spread":0.2705787298671342,"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."}}