{"id":"W3113041327","doi":"10.22148/001c.18238","title":"Sermons as data: Introducing a corpus of 11,955 Danish sermons","year":2020,"lang":"en","type":"article","venue":"Journal of Cultural Analytics","topic":"Media, Religion, Digital Communication","field":"Arts and Humanities","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Danish; Sermon; Corpus linguistics; Metadata; Agency (philosophy); Field (mathematics); Sociology; Resource (disambiguation); Linguistics; Social science; Computer science; Philosophy; World Wide Web; Theology","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004768777,0.0004261224,0.0004785602,0.007674723,0.00359931,0.003399126,0.001232618,0.001305427,0.007463712],"category_scores_gemma":[0.01566268,0.0004082692,0.0003777537,0.007474119,0.002219923,0.001781615,0.003651305,0.001032,0.003042822],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002162019,"about_ca_system_score_gemma":0.003506365,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01560649,"about_ca_topic_score_gemma":0.04732124,"domain_scores_codex":[0.9960325,0.001522031,0.0007418155,0.0008140011,0.0006810502,0.000208543],"domain_scores_gemma":[0.9887601,0.007071051,0.0008206055,0.001400776,0.001531824,0.0004156793],"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":[0.001054251,0.0005946299,0.06950276,0.01460403,0.0002939483,0.01196377,0.2537827,0.0033035,0.03073454,0.07440994,0.3097297,0.2300262],"study_design_scores_gemma":[0.0000312562,0.0000261953,0.03665991,0.001166071,0.00004572412,0.0007083272,0.03731222,0.0004792695,0.00230642,0.002419168,0.9187831,0.00006230031],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"dataset","genre_scores_codex":[0.4766319,0.01903661,0.0385617,0.004959624,0.003581559,0.002757815,0.3425132,0.0008838797,0.1110738],"genre_scores_gemma":[0.5565459,0.006005408,0.09427436,0.00117418,0.0004400733,0.004015823,0.3119793,0.001048917,0.02451615],"genre_candidate":"dataset","genre_consensus":null,"teacher_disagreement_score":0.01560649,"threshold_uncertainty_score":0.03103131,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1288727277294907,"score_gpt":0.2961811416592544,"score_spread":0.1673084139297637,"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."}}