{"id":"W4386266758","doi":"10.1109/access.2023.3309697","title":"MCNN-LSTM: Combining CNN and LSTM to Classify Multi-Class Text in Imbalanced News Data","year":2023,"lang":"en","type":"article","venue":"IEEE Access","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":64,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Computer science; Artificial intelligence; Convolutional neural network; Machine learning; Margin (machine learning); Deep learning; Class (philosophy); Feature (linguistics); Sentence; Document classification; Categorization; Natural language processing","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":[0.0005728624,0.001274465,0.0005917131,0.001069756,0.0003620354,0.0006900115,0.001028789,0.0008176141,0.00148173],"category_scores_gemma":[0.001255963,0.0003298592,0.0005010486,0.001212834,0.0003031387,0.001882767,0.0006585082,0.001017143,0.0007589893],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007505972,"about_ca_system_score_gemma":0.0006361061,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008392334,"about_ca_topic_score_gemma":0.01175682,"domain_scores_codex":[0.9997186,0.00002555256,0.00001685047,0.0001081793,0.00006792093,0.00006295028],"domain_scores_gemma":[0.9996903,0.00007944544,0.00005351731,0.00004054013,0.0001071217,0.00002909697],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0004410241,0.0003168959,0.00510209,0.0001972261,0.0002143979,0.0003702825,0.0001487787,0.09680742,0.03299803,0.001647909,0.01922414,0.8425318],"study_design_scores_gemma":[0.00001432008,0.00008695576,0.001269538,0.00001915265,0.00003999696,0.0000801103,0.0000367758,0.9851351,0.009297798,0.002080008,0.00192492,0.00001525201],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2601503,0.005218315,0.7049825,0.001532168,0.00151438,0.0002502821,0.002126133,0.01495206,0.009273904],"genre_scores_gemma":[0.8432761,0.001177529,0.1420313,0.0007501463,0.000440033,0.0001741954,0.003341642,0.000291201,0.008517942],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008392334,"threshold_uncertainty_score":0.01668698,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1552556872135712,"score_gpt":0.3857469680310411,"score_spread":0.2304912808174699,"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."}}