{"id":"W3147221178","doi":"10.54590/pop.2020.007","title":"Digitizing Humanities in South Africa: Computational linguistic resources, training, and community building","year":2020,"lang":"en","type":"article","venue":"Pop! Public Open Participatory","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Digital humanities; Scarcity; Computer science; Computational linguistics; Field (mathematics); Data science; Knowledge management; World Wide Web; Artificial intelligence","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001336706,0.0001731705,0.0002809884,0.0001481318,0.0005023318,0.001691323,0.001714522,0.0000672518,0.00001298743],"category_scores_gemma":[0.001587174,0.0001759217,0.00002666796,0.0004514139,0.0001737379,0.001027594,0.001702128,0.0007202994,0.000005050418],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006218599,"about_ca_system_score_gemma":0.0001674021,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000940852,"about_ca_topic_score_gemma":0.00003330702,"domain_scores_codex":[0.9980991,0.0005050417,0.0003560613,0.0003458746,0.0002690039,0.0004249517],"domain_scores_gemma":[0.9988688,0.0003816053,0.0001529819,0.0002962435,0.0001068558,0.0001935386],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00001595872,0.0001844948,0.008417809,0.0001486632,0.00004059759,0.00008808283,0.6479104,0.00008473096,0.0001559682,0.3243274,0.0004322423,0.0181936],"study_design_scores_gemma":[0.004142761,0.001165553,0.01347066,0.001007241,0.00007594102,0.00008040784,0.03363794,0.3316915,0.001092896,0.5354797,0.07468851,0.003466927],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8581214,0.004813885,0.1164162,0.004381349,0.0002224672,0.0009717185,0.00003245158,0.001829573,0.01321091],"genre_scores_gemma":[0.9198206,7.536468e-7,0.07882737,0.001205612,0.00005588695,0.00004575954,0.000004440545,0.00001601385,0.00002356803],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6142725,"threshold_uncertainty_score":0.999345,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.253500346954573,"score_gpt":0.3502769815862521,"score_spread":0.09677663463167907,"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."}}