{"id":"W2057505677","doi":"10.1111/j.1467-8640.2007.00293.x","title":"KEYWORD EXTRACTION STRATEGY FOR ITEM BANKS TEXT CATEGORIZATION","year":2007,"lang":"en","type":"article","venue":"Computational Intelligence","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"","keywords":"Categorization; Computer science; Selection (genetic algorithm); Keyword extraction; Natural language processing; Phrase; Sentence; Artificial intelligence; Text categorization; Feature selection; Information retrieval","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":[0.0005329649,0.0001692565,0.0001539846,0.0002734088,0.0001923691,0.0001510877,0.0006072216,0.00008990734,0.0000223208],"category_scores_gemma":[0.0001463424,0.0001787005,0.00009842662,0.0007608148,0.00005608674,0.0009154606,0.00007272683,0.0001362026,0.00005391239],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001351595,"about_ca_system_score_gemma":0.00008251334,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001178619,"about_ca_topic_score_gemma":0.00001727254,"domain_scores_codex":[0.9983733,0.00002657408,0.0004855186,0.0004776028,0.0003412772,0.0002957224],"domain_scores_gemma":[0.9979414,0.0008921009,0.0002238969,0.000280693,0.0005703491,0.00009151287],"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":[0.000009914154,0.00005210963,0.0001068584,0.00000863338,0.00001260751,0.000003421333,0.0001060824,0.1601729,0.0003826218,0.426843,0.000186924,0.4121149],"study_design_scores_gemma":[0.00004736329,0.00009253085,0.002014939,0.00001131558,0.000007120181,0.00001639058,0.00003558829,0.6374245,0.01883545,0.3393651,0.00193246,0.0002172472],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.000826333,0.0001070122,0.996761,0.0001720755,0.0002007821,0.0002974171,0.000002284321,0.0003814257,0.001251718],"genre_scores_gemma":[0.655297,0.000009138666,0.3442036,0.0001263345,0.0000829675,0.0000216273,0.00003614973,0.00001006884,0.0002130914],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6544707,"threshold_uncertainty_score":0.7287196,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04857456591788745,"score_gpt":0.3760418760437714,"score_spread":0.327467310125884,"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."}}