{"id":"W3023453969","doi":"10.1007/978-3-030-47358-7_19","title":"Using Topic Modelling to Improve Prediction of Financial Report Commentary Classes","year":2020,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Computer science; Latent Dirichlet allocation; Class (philosophy); Task (project management); Feature selection; Selection (genetic algorithm); Artificial intelligence; Machine learning; Data mining; Feature (linguistics); Finance; Topic model","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004606154,0.0003853913,0.0006082618,0.0006648265,0.0001479749,0.0001366795,0.001974908,0.0002209159,0.000003006695],"category_scores_gemma":[0.00009398036,0.0003886591,0.0001573412,0.0007518513,0.0002491954,0.0006225666,0.00143877,0.0005606854,0.000001989509],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003700841,"about_ca_system_score_gemma":0.0003903056,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005556561,"about_ca_topic_score_gemma":0.00002169826,"domain_scores_codex":[0.9965929,0.00002224535,0.0007954317,0.00137791,0.0008374315,0.0003740447],"domain_scores_gemma":[0.997726,0.0001488118,0.0004773253,0.001214311,0.0002832981,0.0001502756],"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":[0.00001138129,0.00004487222,0.0001964484,0.00008882315,0.00002385817,0.0003076144,0.0006788278,0.619472,0.005235881,0.01186438,0.00007748012,0.3619984],"study_design_scores_gemma":[0.00008140344,0.0001749868,0.00001960453,0.0002443657,0.00001634195,0.00004028202,8.287468e-8,0.8794293,0.01323822,0.1055838,0.0008596673,0.000311942],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0001960247,0.00009159133,0.9971004,0.0009091377,0.0007996539,0.000403287,0.00001008689,0.0001830473,0.0003067906],"genre_scores_gemma":[0.08219323,0.00001354676,0.9151703,0.002134426,0.0004264558,0.000006399275,0.000006386866,0.00002164837,0.00002762792],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3616865,"threshold_uncertainty_score":0.9998565,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03398848257873614,"score_gpt":0.2817074990245209,"score_spread":0.2477190164457847,"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."}}