{"id":"W2151674174","doi":"","title":"Multilabel Subject-Based Classification of Poetry","year":2015,"lang":"en","type":"article","venue":"Digital Access to Libraries (Université catholique de Louvain (UCL), l'Université de Namur (UNamur) and the Université Saint-Louis (USL-B))","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Poetry; Computer science; Latent Dirichlet allocation; Artificial intelligence; Context (archaeology); Support vector machine; Set (abstract data type); Style (visual arts); Subject (documents); Natural language processing; Task (project management); Machine learning; Simple (philosophy); Pattern recognition (psychology); Topic model; Linguistics; World Wide Web; Literature; Engineering; Art","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":[0.0007174124,0.0007382304,0.000931189,0.001569652,0.0009511795,0.0009514779,0.004685605,0.000459038,0.00004844915],"category_scores_gemma":[0.0002759276,0.0007534347,0.0004679243,0.003281376,0.00103341,0.002725363,0.003629043,0.0005937907,0.00003742406],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001937428,"about_ca_system_score_gemma":0.0007553437,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006364866,"about_ca_topic_score_gemma":0.00008788687,"domain_scores_codex":[0.9959646,0.0004149644,0.0005058551,0.001228135,0.0008413125,0.001045066],"domain_scores_gemma":[0.9953988,0.0006607035,0.0007150607,0.001583071,0.0006874733,0.0009548627],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.004507473,0.0005787247,0.01599228,0.0001782737,0.0005931542,0.000997239,0.067161,0.002198011,0.001841072,0.8698688,0.005489279,0.03059473],"study_design_scores_gemma":[0.02301098,0.00171083,0.04753514,0.0006192144,0.001223807,0.0005542712,0.01304398,0.1497943,0.02306783,0.04639215,0.6876598,0.005387663],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3819172,0.0007003664,0.5011151,0.009633941,0.0001877722,0.001415457,0.0002201339,0.001298669,0.1035114],"genre_scores_gemma":[0.9786014,0.0001353911,0.01380557,0.0009823003,0.00005441743,0.000007886979,0.0001188289,0.00007414419,0.006220058],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8234766,"threshold_uncertainty_score":0.9994917,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0171923457182645,"score_gpt":0.2303370288841324,"score_spread":0.2131446831658679,"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."}}