{"id":"W2586378516","doi":"10.24251/hicss.2017.110","title":"Introduction to Text Mining in Big Data Analytics Minitrack","year":2017,"lang":"en","type":"article","venue":"Proceedings of the ... Annual Hawaii International Conference on System Sciences/Proceedings of the Annual Hawaii International Conference on System Sciences","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"","keywords":"Computer science; Big data; Data science; Analytics; 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","sts","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.005386007,0.0006496806,0.0008107495,0.001072987,0.00172473,0.003030469,0.03154622,0.0002168387,0.00002674589],"category_scores_gemma":[0.000454897,0.0004485468,0.0002587015,0.001881035,0.001832296,0.005072482,0.005468757,0.0005578721,0.00006100881],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004409636,"about_ca_system_score_gemma":0.0006549077,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005147815,"about_ca_topic_score_gemma":0.00006524874,"domain_scores_codex":[0.9909797,0.00004529232,0.00173845,0.002314262,0.004095681,0.0008266677],"domain_scores_gemma":[0.9904214,0.0001824208,0.003105727,0.001249209,0.004776382,0.000264909],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","study_design_scores_codex":[0.00005641721,0.0001665606,0.004682872,0.00009749473,0.00005958457,9.641973e-7,0.001554205,0.00008671672,0.0007255527,0.9818193,0.005817189,0.004933186],"study_design_scores_gemma":[0.001482693,0.001232865,0.02308116,0.007999377,0.00008667323,0.0002615091,0.9213874,0.02990633,0.002672342,0.003836519,0.006403205,0.0016499],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.04832629,0.00001476648,0.0005106921,0.03631885,0.006388068,0.001037601,0.001107593,0.0001438554,0.9061522],"genre_scores_gemma":[0.9920934,0.00002131644,0.004923142,0.0001444288,0.001095238,0.0000967171,0.00000801104,0.00002433621,0.00159343],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9779828,"threshold_uncertainty_score":0.9997966,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1186369289700182,"score_gpt":0.334029464992193,"score_spread":0.2153925360221747,"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."}}