{"id":"W2252545675","doi":"10.1007/978-3-319-25252-0_18","title":"Ontology-Based Topic Labeling and Quality Prediction","year":2015,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"York University","funders":"","keywords":"Computer science; Latent Dirichlet allocation; Topic model; Reliability (semiconductor); Probabilistic logic; Ontology; Coherence (philosophical gambling strategy); Quality (philosophy); Artificial intelligence; Information retrieval; Natural language processing; Semantics (computer science); Machine learning; Data mining","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002668828,0.001077233,0.001144381,0.007864974,0.001190331,0.003012697,0.001868736,0.001287579,0.004678779],"category_scores_gemma":[0.01119329,0.0005493474,0.001789817,0.007539602,0.0005827153,0.004884536,0.002103999,0.001758471,0.00344136],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001684198,"about_ca_system_score_gemma":0.002663848,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01120113,"about_ca_topic_score_gemma":0.01596886,"domain_scores_codex":[0.9969625,0.0004640749,0.0002700999,0.0007242335,0.001316984,0.0002621508],"domain_scores_gemma":[0.9936928,0.002568817,0.0004890771,0.0007708321,0.002213885,0.0002647051],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0005502708,0.0003872318,0.01397147,0.0008923697,0.0002186506,0.0002211582,0.0007669025,0.0179488,0.03008731,0.01389293,0.03521571,0.8858472],"study_design_scores_gemma":[0.0001097973,0.0001598788,0.0188102,0.0002249178,0.0004830902,0.0005512571,0.0007067506,0.8432064,0.03183243,0.05161928,0.05214922,0.0001467673],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04341865,0.003124633,0.9280542,0.0006504987,0.0003480347,0.0004118287,0.007114962,0.008203916,0.008673312],"genre_scores_gemma":[0.2901602,0.002034669,0.6764861,0.000138092,0.0003524285,0.0004316369,0.02076242,0.001153326,0.008481096],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01120113,"threshold_uncertainty_score":0.02227187,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0454640940380162,"score_gpt":0.31517178953092,"score_spread":0.2697076954929037,"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."}}