{"id":"W3169915179","doi":"","title":"History of Text Mining over a Quarter of a Century and its Future Potential","year":2021,"lang":"en","type":"article","venue":"IEICE Technical Report; IEICE Tech. Rep.","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"","keywords":"Quarter (Canadian coin); Computer science; History; Data science; Archaeology","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008122302,0.0003306756,0.0006621166,0.0002554027,0.00005874957,0.00004831663,0.0009470115,0.0004720941,0.00006034658],"category_scores_gemma":[0.0008276221,0.0003067705,0.0002368167,0.0007654341,0.000188053,0.000590278,0.0008506119,0.0006032239,0.000001756963],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002405594,"about_ca_system_score_gemma":0.0005866351,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004295622,"about_ca_topic_score_gemma":0.00001266196,"domain_scores_codex":[0.9964332,0.0001029356,0.001148827,0.001007164,0.0008834953,0.0004243647],"domain_scores_gemma":[0.9965059,0.0001630548,0.001044993,0.001522002,0.0005970577,0.0001669741],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00007050545,0.0005196063,0.0003985462,0.0006593672,0.00009651735,0.00966776,0.0009101892,0.000001418868,0.9158438,0.02085452,0.01287911,0.03809869],"study_design_scores_gemma":[0.003756698,0.002056279,0.01645613,0.003962909,0.0007714105,0.08150777,0.001377351,0.004635957,0.6908227,0.03528757,0.154473,0.004892238],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4941246,0.2428923,0.2272252,0.006784246,0.004364277,0.002249909,0.00004772393,0.007804076,0.01450762],"genre_scores_gemma":[0.7945821,0.0002003182,0.2042974,0.0002374636,0.00009858977,0.00002593892,0.000006631379,0.00002974632,0.0005217967],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3004575,"threshold_uncertainty_score":0.9999384,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008353451844343487,"score_gpt":0.2570536555688936,"score_spread":0.2487002037245502,"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."}}