{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004803553,0.001545209,0.0008802346,0.001328916,0.0003989335,0.001732676,0.0005926309,0.001050379,0.001069045],"category_scores_gemma":[0.01694618,0.0002510884,0.0006055849,0.001363412,0.000476574,0.002989383,0.001130849,0.001491057,0.000579446],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006343467,"about_ca_system_score_gemma":0.0006797431,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004025322,"about_ca_topic_score_gemma":0.003376534,"domain_scores_codex":[0.9975852,0.001368509,0.000220659,0.0003600507,0.0002777321,0.0001878602],"domain_scores_gemma":[0.9905129,0.007111822,0.0005176643,0.0006286599,0.001033922,0.0001950968],"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":[0.002618794,0.001732454,0.04365767,0.0005124541,0.0005619398,0.0002406802,0.0003725006,0.2195056,0.02276054,0.002526912,0.006730913,0.6987795],"study_design_scores_gemma":[0.00003710021,0.0003452602,0.005207418,0.00003475945,0.0001077869,0.000095784,0.0002508626,0.9836971,0.007920677,0.001545021,0.0007328654,0.00002541766],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8821281,0.002890209,0.1069911,0.0009846983,0.0003470251,0.0001708081,0.000966903,0.001493571,0.004027612],"genre_scores_gemma":[0.9701203,0.0005524455,0.02693491,0.00008767824,0.00006022298,0.00004691002,0.001320848,0.00004878168,0.000827835],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.004803553,"threshold_uncertainty_score":0.02540392,"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."}}