{"id":"W2131347559","doi":"10.4018/978-1-60960-625-1.ch004","title":"A Cognitive-Based Approach to Identify Topics in Text Using the Web as a Knowledge Source","year":2011,"lang":"en","type":"book-chapter","venue":"IGI Global eBooks","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"Royal Military College of Canada","funders":"","keywords":"Computer science; Meaning (existential); Identification (biology); Ambiguity; Representation (politics); Cluster analysis; Artificial intelligence; Knowledge extraction; Natural language processing; Information retrieval; Psychology","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":[0.0003173996,0.0005281495,0.0005723044,0.0002901244,0.0001477111,0.0002221222,0.001882034,0.0003695917,0.00001028427],"category_scores_gemma":[0.00005573965,0.0004469492,0.0003111913,0.0001706433,0.0001648267,0.0001173836,0.0008938521,0.0005030935,0.0001310495],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004028459,"about_ca_system_score_gemma":0.0004765876,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001627013,"about_ca_topic_score_gemma":0.0002311921,"domain_scores_codex":[0.9975477,0.00008435753,0.000508389,0.0009490286,0.0004335215,0.0004769794],"domain_scores_gemma":[0.9981249,0.00007571778,0.0002793719,0.001111907,0.0002434949,0.0001645873],"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":[0.0000158418,0.0000462499,0.00002096614,0.00002415053,0.000055898,0.00002862468,0.000424285,0.00002898213,0.00002755446,0.9586434,0.0001795405,0.04050445],"study_design_scores_gemma":[0.0009441253,0.000223334,0.00007719707,0.001333361,0.0002934854,0.0001132751,0.00006210683,0.01751582,0.0009059692,0.8783373,0.0981326,0.002061427],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.0001073931,0.000156684,0.4404245,0.00002286858,0.00006735682,0.0004755551,0.000009214496,0.0002011784,0.5585352],"genre_scores_gemma":[0.7867155,0.000007012315,0.09545667,0.00307416,0.0005091419,0.00022048,0.000007454872,0.0001611885,0.1138484],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7866081,"threshold_uncertainty_score":0.9997982,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05338759894227268,"score_gpt":0.3263738601881291,"score_spread":0.2729862612458565,"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."}}