{"id":"W2006341631","doi":"10.4018/jdm.2008100105","title":"Ontology for Data Mining and its Application to Mining Incomplete Data","year":2008,"lang":"en","type":"article","venue":"Journal of Database Management","topic":"Semantic Web and Ontologies","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"Saint Mary's University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Ontology; Computer science; Data mining; Knowledge extraction; Ontology-based data integration; Process ontology; Upper ontology; Domain (mathematical analysis); Data science; Domain knowledge; Information retrieval; Knowledge management","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0168137,0.001164767,0.002185116,0.009527826,0.002787482,0.006830942,0.002835182,0.002678482,0.002593337],"category_scores_gemma":[0.02777234,0.001119433,0.004021605,0.01454735,0.006645591,0.01171316,0.00558882,0.004807591,0.001037549],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002816523,"about_ca_system_score_gemma":0.00461474,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004625624,"about_ca_topic_score_gemma":0.003979153,"domain_scores_codex":[0.985602,0.006396089,0.002275594,0.001242851,0.004201879,0.0002815897],"domain_scores_gemma":[0.9835895,0.0112779,0.0009387279,0.002296966,0.001556959,0.0003399046],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00003180339,0.00006641127,0.0008655903,0.0009909656,0.0002067761,0.0005138846,0.00150636,0.009354806,0.0008954046,0.8194273,0.007062768,0.1590779],"study_design_scores_gemma":[0.00002139304,0.00002695549,0.0004615051,0.0005858939,0.00008191505,0.0006210295,0.0005149139,0.06521989,0.00139608,0.8146369,0.1163508,0.00008264434],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0009192966,0.002722963,0.9895,0.001904509,0.0001694368,0.000168531,0.0002406429,0.0004069578,0.00396766],"genre_scores_gemma":[0.02089819,0.004627782,0.9716887,0.0003971393,0.0002510094,0.0004829971,0.000608629,0.0001089606,0.0009365514],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0168137,"threshold_uncertainty_score":0.08892035,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1642859759300605,"score_gpt":0.3422706804343884,"score_spread":0.1779847045043279,"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."}}