{"id":"W4394956176","doi":"10.3390/make6020041","title":"Enhancing Legal Sentiment Analysis: A Convolutional Neural Network–Long Short-Term Memory Document-Level Model","year":2024,"lang":"en","type":"article","venue":"Machine Learning and Knowledge Extraction","topic":"Artificial Intelligence in Law","field":"Social Sciences","cited_by":24,"is_retracted":false,"has_abstract":true,"ca_institutions":"Athabasca University","funders":"","keywords":"Term (time); Convolutional neural network; Computer science; Long short term memory; Sentiment analysis; Natural language processing; Artificial intelligence; Information retrieval; Artificial neural network; Recurrent neural network","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00146127,0.0001847283,0.000219543,0.0002149014,0.001236695,0.0004704235,0.0001042439,0.0001300321,0.0004535887],"category_scores_gemma":[0.00009363471,0.0001868694,0.0001753322,0.0006255624,0.0001885299,0.0006546386,0.00006494462,0.0006351979,0.00009012633],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002280273,"about_ca_system_score_gemma":0.0001601212,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001828812,"about_ca_topic_score_gemma":0.01878396,"domain_scores_codex":[0.9980448,0.0003713612,0.0003594332,0.0004526262,0.0003344667,0.0004373398],"domain_scores_gemma":[0.9993278,0.0002635655,0.00006668372,0.000092176,0.00009759413,0.0001521936],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001488599,0.0002836828,0.06158057,0.00017216,0.001438703,0.0001167869,0.03248915,0.5117323,0.008498983,0.05869933,0.0007919511,0.3240475],"study_design_scores_gemma":[0.00004531781,0.00003312436,0.001889182,0.00006719485,0.0004004689,0.0000101481,0.001114827,0.9850373,0.0004167044,0.0007068462,0.01000898,0.0002698651],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7327635,0.01203135,0.2064819,0.001169357,0.003279361,0.0004770184,0.00001021437,0.0009031026,0.04288414],"genre_scores_gemma":[0.9763156,0.0001461095,0.0003976187,0.00001802769,0.001122345,0.00002251463,0.00003188547,0.00002015707,0.02192572],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.473305,"threshold_uncertainty_score":0.9991207,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03887216470533473,"score_gpt":0.3762450044228615,"score_spread":0.3373728397175267,"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."}}