{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002519094,0.0001472722,0.0001180398,0.0002472433,0.00007370016,0.0004071466,0.0008940719,0.00007670767,0.000004944014],"category_scores_gemma":[0.0001231538,0.0001400477,0.00001987578,0.0005601778,0.00003425457,0.001286346,0.0007719047,0.0001800129,0.00009020637],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007620501,"about_ca_system_score_gemma":0.00003418062,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005098803,"about_ca_topic_score_gemma":0.000002220187,"domain_scores_codex":[0.9989894,0.00001694631,0.0001609418,0.0005411881,0.00009655448,0.0001949833],"domain_scores_gemma":[0.9988191,0.0001900226,0.00002473445,0.0008875146,0.00002819763,0.00005040084],"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":[8.676244e-7,0.00002347563,0.00009825209,0.0001527444,0.00003624986,0.000005839518,0.0004128938,0.00001672452,0.02223007,0.1486993,0.002350505,0.825973],"study_design_scores_gemma":[0.00006077505,0.00001190403,0.001815586,0.00008393756,0.0000108021,0.00001295044,0.00002606875,0.9251232,0.001904855,0.0002897153,0.0705009,0.0001593432],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008288466,0.006318005,0.9817908,0.0003773586,0.0007573832,0.0002188747,0.00002400855,0.001592662,0.0006323743],"genre_scores_gemma":[0.9438424,0.0001292412,0.05555006,0.000009459266,0.0001516366,0.00004043996,0.0000644263,0.00002555523,0.0001867975],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9355539,"threshold_uncertainty_score":0.5710978,"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."}}