{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003370133,0.0001827046,0.0002427622,0.0004462007,0.0001251985,0.0007097174,0.004120491,0.0001197357,0.000008184219],"category_scores_gemma":[0.0001844186,0.0001727936,0.00002087893,0.001796335,0.00007503873,0.00182333,0.002349402,0.000225453,0.0002354718],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004581357,"about_ca_system_score_gemma":0.0000550068,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000132686,"about_ca_topic_score_gemma":0.0003113922,"domain_scores_codex":[0.9981015,0.00004881342,0.0003401162,0.0008190055,0.0002602905,0.0004302508],"domain_scores_gemma":[0.9979042,0.0001686605,0.0001152844,0.001666744,0.000041793,0.0001033223],"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":[0.00004031753,0.0003398743,0.1703411,0.0001076167,0.00005336578,0.0001308385,0.001947741,0.0005907568,0.0183096,0.0210444,0.1524752,0.6346192],"study_design_scores_gemma":[0.003494161,0.0001582469,0.3949886,0.0002005687,0.00001363328,0.00001151684,0.0008979039,0.4931268,0.01349057,0.008055352,0.08426645,0.001296193],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7069339,0.0002162544,0.2434696,0.03965316,0.002461603,0.001141395,0.00004387033,0.003963279,0.002116932],"genre_scores_gemma":[0.9927286,0.0001250742,0.005332245,0.0009082628,0.00003768362,0.00007046541,0.00002035441,0.00001560926,0.0007617046],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.633323,"threshold_uncertainty_score":0.7656966,"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."}}