{"id":"W2624261825","doi":"10.1146/annurev-statistics-031017-100547","title":"Words, Words, Words: How the Digital Humanities Are Integrating Diverse Research Fields to Study People","year":2018,"lang":"en","type":"article","venue":"Annual Review of Statistics and Its Application","topic":"Topic Modeling","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Digital humanities; Scholarship; Mainstream; Field (mathematics); Big data; Interdisciplinarity; Data science; Digital scholarship; Political science; Sociology; Public relations; Social science; Library science; Computer science","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":[],"consensus_categories":[],"category_scores_codex":[0.0007948492,0.00009844817,0.0001851943,0.00005146055,0.0002797906,0.0001927771,0.0005508841,0.00002336941,0.000008065372],"category_scores_gemma":[0.0004682943,0.00006928246,0.00001729795,0.0003613934,0.0000522257,0.000231763,0.0004245677,0.0001485829,0.00001493475],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001621792,"about_ca_system_score_gemma":0.00002860591,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007208391,"about_ca_topic_score_gemma":0.0002188844,"domain_scores_codex":[0.9988073,0.00008074294,0.0002506705,0.0002942847,0.0003929676,0.0001740562],"domain_scores_gemma":[0.9985023,0.0002556905,0.000138889,0.0004343925,0.0006194201,0.00004928494],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000003716728,0.00008577483,0.0005219983,0.0005332666,0.00001636811,0.000001044615,0.02006155,0.00000104148,0.00000684779,0.1706394,0.005702449,0.8024266],"study_design_scores_gemma":[0.001849427,0.00626049,0.04872682,0.01478093,0.0002812906,0.00003709954,0.276132,0.1099483,0.0004162331,0.07932885,0.4595214,0.00271722],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02097775,0.003976411,0.9701412,0.002586545,0.00008041943,0.001390002,0.0001372317,0.00002807038,0.0006823755],"genre_scores_gemma":[0.9900478,0.00221452,0.006903566,0.0003724441,0.0001208605,0.000109716,0.000008584805,0.000006387562,0.000216128],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.96907,"threshold_uncertainty_score":0.2825257,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06264499503292599,"score_gpt":0.3498613314029844,"score_spread":0.2872163363700584,"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."}}