{"id":"W2234779292","doi":"10.1145/2847557.2847560","title":"Machine learning meets visualization for extracting insights from text data","year":2016,"lang":"en","type":"article","venue":"AI Matters","topic":"Data Visualization and Analytics","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; Dalhousie University","funders":"Natural Sciences and Engineering Research Council of Canada; National Aeronautics and Space Administration; Boeing","keywords":"Computer science; Visual analytics; Visualization; Process (computing); Data science; Analytics; Text mining; Data visualization; Biomedical text mining; Path (computing); Natural language processing; Information retrieval; Artificial intelligence","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0001391638,0.00009818211,0.0001030617,0.00007948055,0.0001331786,0.0002079083,0.0008563414,0.0000324362,0.00005278298],"category_scores_gemma":[0.0001257846,0.00007186699,0.00002211366,0.0001595842,0.00001797143,0.001463246,0.0003525755,0.00003999878,0.0001105821],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001949766,"about_ca_system_score_gemma":0.00002123401,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003923555,"about_ca_topic_score_gemma":0.00001977646,"domain_scores_codex":[0.9990376,0.00005570637,0.0001995835,0.0003912589,0.0001676362,0.0001482252],"domain_scores_gemma":[0.9989316,0.0002409081,0.0001282435,0.0005892454,0.0000513344,0.00005865643],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00003247822,0.0002689525,0.003984576,0.00008571968,0.0002084247,0.00002127676,0.002250875,0.0002561767,0.05644667,0.2867336,0.3898373,0.259874],"study_design_scores_gemma":[0.0003920193,0.00001884294,0.0001594275,0.00005401799,0.00001082456,0.000001257405,0.00002096547,0.4602032,0.001206703,0.001264957,0.5365129,0.0001549879],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0002540196,0.00004735398,0.9776817,0.02145883,0.0002171261,0.00007953647,0.00005891217,0.0001475347,0.0000549959],"genre_scores_gemma":[0.8935366,0.0001220498,0.03716633,0.06492107,0.0003283712,0.00001427315,0.001959783,0.00006404983,0.001887534],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9405153,"threshold_uncertainty_score":0.2930651,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04219726391390411,"score_gpt":0.3290350505911965,"score_spread":0.2868377866772924,"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."}}