{"id":"W2039979754","doi":"10.1109/isspa.2012.6310552","title":"Automatic Document Topic Identification using Wikipedia Hierarchical Ontology","year":2012,"lang":"en","type":"article","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Ontology; Information retrieval; Identification (biology); Document clustering; Cluster analysis; Construct (python library); Hierarchical clustering; Data mining; Artificial intelligence","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":[],"consensus_categories":[],"category_scores_codex":[0.000291089,0.00008955315,0.0001347884,0.0001249866,0.00007405057,0.00006489854,0.0004601775,0.00005031367,0.00008026506],"category_scores_gemma":[0.00003912534,0.00007785698,0.00005185489,0.0002556798,0.00003673523,0.0009955928,0.0001768216,0.00008370664,0.00006755705],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009562404,"about_ca_system_score_gemma":0.00002008865,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002530421,"about_ca_topic_score_gemma":0.000009232007,"domain_scores_codex":[0.9989858,0.0000738668,0.0002653196,0.0002057489,0.0001885632,0.000280699],"domain_scores_gemma":[0.9991941,0.00006060729,0.00008983034,0.0005323908,0.00003414164,0.00008896469],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[6.565606e-7,0.0001422439,0.006025184,0.00001341673,0.0000281791,0.000002618716,0.0007239974,0.00001613339,0.007986967,0.7411171,0.0002844579,0.243659],"study_design_scores_gemma":[0.0004713671,0.00007805788,0.06248217,0.00002724251,0.0000866536,0.0001122275,0.00006045048,0.5938627,0.05722787,0.2782495,0.006512328,0.0008294033],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1226161,0.00007008545,0.8752747,0.0003802242,0.0001615534,0.00009008162,6.035395e-8,0.0004036936,0.001003481],"genre_scores_gemma":[0.6414125,0.000003181781,0.3581572,0.0001422927,0.00005244753,0.000009438721,7.497961e-7,0.000003039011,0.0002191927],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5938466,"threshold_uncertainty_score":0.3174916,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02265378680570878,"score_gpt":0.3276773295832177,"score_spread":0.3050235427775089,"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."}}