{"id":"W1888496803","doi":"10.1007/978-3-642-02976-9_46","title":"Automatic Detecting Documents Containing Personal Health Information","year":2009,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Computer science; Artificial intelligence; Decision tree; Support vector machine; Natural language processing; Categorization; Information retrieval; Lexical analysis; Text categorization; Naive Bayes classifier; The Internet; Task (project management); Supervised learning; Machine learning; World Wide Web","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":[0.000607923,0.0007091867,0.0008068571,0.00548948,0.0007471745,0.001487578,0.0006832412,0.001070126,0.003000004],"category_scores_gemma":[0.002602601,0.0002719341,0.0005332294,0.002634057,0.0002861106,0.001016309,0.0004812782,0.0005128427,0.002831496],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005197352,"about_ca_system_score_gemma":0.0008267159,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003369218,"about_ca_topic_score_gemma":0.004894771,"domain_scores_codex":[0.9994276,0.00005338047,0.00006495396,0.0001356933,0.0002489237,0.00006941414],"domain_scores_gemma":[0.9971601,0.001462791,0.0002970033,0.0002113659,0.000741021,0.0001276858],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0009009736,0.0003798194,0.01746262,0.001162597,0.0001002116,0.00138932,0.0004221135,0.0009981332,0.1466109,0.001608904,0.04296267,0.7860017],"study_design_scores_gemma":[0.0002175566,0.000969606,0.1318672,0.0007058643,0.001278007,0.01517237,0.00164201,0.1338575,0.5569432,0.008992075,0.1481506,0.0002040495],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5632409,0.02489999,0.3223805,0.002469023,0.002132544,0.001324567,0.03838737,0.02024134,0.02492367],"genre_scores_gemma":[0.5754009,0.006135859,0.3485603,0.0005860273,0.001078212,0.0002862317,0.03830288,0.0005143533,0.0291352],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.00548948,"threshold_uncertainty_score":0.01003599,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01851048022841444,"score_gpt":0.268608716320946,"score_spread":0.2500982360925316,"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."}}