{"id":"W4394855929","doi":"10.1515/cllt-2023-0104","title":"Corpus-based discourse analysis: from meta-reflection to accountability","year":2024,"lang":"en","type":"article","venue":"Corpus Linguistics and Linguistic Theory","topic":"Discourse Analysis in Language Studies","field":"Arts and Humanities","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Australian Research Data Commons; Simon Fraser University; University of Sydney","keywords":"Accountability; Transparency (behavior); Objectivity (philosophy); Reflexivity; Computer science; Corpus linguistics; Consistency (knowledge bases); Subjectivity; Analytics; Data science; Reflection (computer programming); Discourse analysis; Phenomenon; Epistemology; Linguistics; Sociology; Natural language processing; Political science; Artificial intelligence; Social science; Programming language; Philosophy","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0009894955,0.0004451928,0.0008636234,0.0005294365,0.0005206843,0.0008524825,0.0002688509,0.00007437427,0.002536039],"category_scores_gemma":[0.005617981,0.0003388257,0.0005654879,0.0003556853,0.0006458539,0.00002673433,0.0001262024,0.0002981088,0.0001086351],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000787789,"about_ca_system_score_gemma":0.0001161677,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001683378,"about_ca_topic_score_gemma":0.004528697,"domain_scores_codex":[0.9976368,0.0001697561,0.0005781447,0.0008351872,0.0003840354,0.0003961009],"domain_scores_gemma":[0.9969619,0.001481395,0.0001255677,0.0006338585,0.0005980307,0.0001992284],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001076194,0.000135059,0.0003332643,0.00008982736,0.0112857,0.00009580814,0.02225286,0.0003752208,0.00001520239,0.9609221,0.0006396343,0.003747671],"study_design_scores_gemma":[0.0002729688,0.0001835666,0.0002227214,0.0001488503,0.07044557,8.926394e-7,0.006098666,0.006710163,0.000105128,0.1997189,0.7150955,0.000997097],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.1203969,0.1229894,0.07037655,0.0008560695,0.03903935,0.00186195,0.006397379,0.002679638,0.6354027],"genre_scores_gemma":[0.9889687,0.0000562422,0.0005275541,0.0004974596,0.006094821,0.00006919583,0.0001572421,0.00005690494,0.003571925],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8685718,"threshold_uncertainty_score":0.9999064,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04261411326796034,"score_gpt":0.3263412858121069,"score_spread":0.2837271725441466,"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."}}