{"id":"W4386753352","doi":"10.21203/rs.3.rs-3343151/v1","title":"Homogenous Ensemble Boosting Approach to Improve the Consistency in the Accuracy of Text Data Classification","year":2023,"lang":"en","type":"preprint","venue":"Research Square","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; New Brunswick Innovation Foundation","keywords":"Sentiment analysis; Computer science; Consistency (knowledge bases); Artificial intelligence; Globe; The Internet; Machine learning; Boosting (machine learning); Unstructured data; Data science; Natural language processing; Data mining; Big data; World Wide Web","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.01028422,0.0001736138,0.0002989772,0.0004878507,0.0003946692,0.0006934247,0.007536941,0.0001262929,0.000004614013],"category_scores_gemma":[0.002722785,0.0001058815,0.0001138228,0.00198446,0.0001180076,0.0001984843,0.007203601,0.001073018,0.0000717854],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008030461,"about_ca_system_score_gemma":0.0005204189,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008956874,"about_ca_topic_score_gemma":0.0001005375,"domain_scores_codex":[0.995095,0.001160303,0.0005872851,0.001040341,0.001587982,0.0005291601],"domain_scores_gemma":[0.9915037,0.002908857,0.0002576834,0.004822569,0.0004393263,0.00006787638],"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":[0.00008823456,0.002266931,0.01504789,0.003495858,0.0007294109,0.00007785256,0.1062157,0.007798439,0.01003216,0.1575386,0.0800778,0.6166312],"study_design_scores_gemma":[0.0003143214,0.0001443614,0.03674452,0.0007316515,0.0000347208,0.00000642334,0.02213626,0.9292763,0.0004444267,0.00484491,0.004882409,0.000439653],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1433083,0.01013829,0.6554655,0.0878488,0.002932144,0.02411,0.00080571,0.0006941739,0.074697],"genre_scores_gemma":[0.9917064,0.0001869413,0.006921559,0.00007474185,0.0001807799,0.0002823562,0.0003004873,0.00001964083,0.0003271223],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9214779,"threshold_uncertainty_score":0.9978328,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3689404806849977,"score_gpt":0.4456225909170176,"score_spread":0.07668211023201982,"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."}}