{"id":"W4394987794","doi":"10.1016/j.datak.2024.102306","title":"Effective text classification using BERT, MTM LSTM, and DT","year":2024,"lang":"en","type":"article","venue":"Data & Knowledge Engineering","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":56,"is_retracted":false,"has_abstract":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada); University of Calgary","funders":"","keywords":"Security token; Computer science; Artificial intelligence; Encoder; Binary classification; Transformer; Recall; Deep learning; Long short term memory; Natural language processing; Artificial neural network; Machine learning; Recurrent neural network; Support vector machine","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":[0.0006206296,0.0008233437,0.0007244822,0.001811987,0.0006673686,0.001094075,0.001024357,0.00129214,0.005158818],"category_scores_gemma":[0.002448098,0.0002291545,0.0006030879,0.001813399,0.0003055074,0.002656406,0.0007310713,0.001283318,0.003326725],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009054172,"about_ca_system_score_gemma":0.001572894,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007583996,"about_ca_topic_score_gemma":0.00974217,"domain_scores_codex":[0.9995552,0.00007035082,0.00004527409,0.0001395463,0.0001268222,0.0000628143],"domain_scores_gemma":[0.9990849,0.0003254322,0.00007557225,0.0001244204,0.0003266997,0.00006282092],"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":[0.0002427495,0.0001341855,0.0007072202,0.0001461462,0.00004037334,0.00009943236,0.00004500004,0.02009593,0.02194989,0.004845452,0.0138783,0.9378154],"study_design_scores_gemma":[0.0000180675,0.00007866747,0.000664972,0.00002412015,0.00003873727,0.0001180951,0.00003939693,0.9720643,0.01342392,0.008044233,0.005468566,0.00001688484],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04909409,0.00225709,0.9276817,0.001263351,0.001143188,0.0001620683,0.001718087,0.009320917,0.007359538],"genre_scores_gemma":[0.4653713,0.001210194,0.5054748,0.0007186317,0.0007777089,0.0002237309,0.004140392,0.0004296021,0.02165369],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007583996,"threshold_uncertainty_score":0.01725793,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04931219236959951,"score_gpt":0.3094819476933262,"score_spread":0.2601697553237267,"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."}}