{"id":"W4248349546","doi":"10.1007/978-0-387-39940-9_3794","title":"Text Data Mining","year":2009,"lang":"en","type":"book-chapter","venue":"Encyclopedia of Database Systems","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Information retrieval; Data science; Data mining","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":[0.0005042971,0.0003967745,0.0006005181,0.0003903019,0.0000778538,0.0001254038,0.005199341,0.0002995494,0.00005998773],"category_scores_gemma":[0.0001363385,0.0003698322,0.00007695149,0.0001198173,0.0001095465,0.001109728,0.001861613,0.0003142877,0.0002829788],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004650091,"about_ca_system_score_gemma":0.0002093984,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003410862,"about_ca_topic_score_gemma":0.000008660669,"domain_scores_codex":[0.9971206,0.00003033454,0.0008553441,0.001030198,0.0006746503,0.000288897],"domain_scores_gemma":[0.9926645,0.0001786838,0.0008426399,0.006107657,0.0001102084,0.0000963489],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000002765169,0.00002903966,0.00001656457,0.0001680069,0.00005457353,0.00003821282,0.00007756065,0.000001724876,0.00002619844,0.5974157,0.2108848,0.1912849],"study_design_scores_gemma":[0.0001485269,0.00005131445,0.00001397214,0.0004753632,0.00003153059,0.00001762009,0.00003940814,0.001113596,0.00001864066,0.001188691,0.9964935,0.0004078292],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.000004735462,0.005747577,0.03921055,0.0003503767,0.001425667,0.0005084727,0.001086347,0.0006657619,0.9510005],"genre_scores_gemma":[0.001088754,0.006849987,0.04515737,0.00006650325,0.0005917365,0.00002634636,0.00289811,0.00006678874,0.9432544],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.7856088,"threshold_uncertainty_score":0.9998754,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04663954244922323,"score_gpt":0.2692034092807251,"score_spread":0.2225638668315018,"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."}}