{"id":"W4392374041","doi":"10.20944/preprints202402.1634.v1","title":"Enhancing Legal Sentiment Analysis: A CNN-LSTM Document-Level Model","year":2024,"lang":"en","type":"preprint","venue":"Preprints.org","topic":"Artificial Intelligence in Law","field":"Social Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Athabasca University","funders":"","keywords":"Sentiment analysis; Computer science; Natural language processing; Artificial intelligence","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003013964,0.0006012571,0.0002479891,0.0005163468,0.0002182061,0.0007186154,0.0006055287,0.0005929046,0.002199351],"category_scores_gemma":[0.000972347,0.000179536,0.0004343379,0.0004677608,0.0002012815,0.0008091634,0.0003821407,0.0009094016,0.001035989],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001060626,"about_ca_system_score_gemma":0.000860439,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02145597,"about_ca_topic_score_gemma":0.02449702,"domain_scores_codex":[0.999905,0.00001211173,0.000005461474,0.00002732337,0.00002422314,0.00002594037],"domain_scores_gemma":[0.9998643,0.00002886917,0.00001906699,0.00001050339,0.00006740566,0.00000978016],"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":[0.0003053449,0.0003524837,0.01026245,0.0002110052,0.0002129546,0.0003910378,0.0002562361,0.2625569,0.03857946,0.01310307,0.03997345,0.6337955],"study_design_scores_gemma":[0.000004978717,0.00001868671,0.0008373641,0.0000110651,0.0000222986,0.0000174485,0.00001553592,0.9931442,0.002125572,0.001949115,0.001848933,0.000004953587],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.3170261,0.002868981,0.620792,0.005722429,0.001217764,0.0002493171,0.004106347,0.005396183,0.04262098],"genre_scores_gemma":[0.9192004,0.0009887198,0.05914005,0.0006415048,0.0002108015,0.00009603342,0.003138132,0.0001079241,0.01647638],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02145597,"threshold_uncertainty_score":0.04266214,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2204475637884853,"score_gpt":0.4413228074950138,"score_spread":0.2208752437065286,"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."}}