{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.1964737,0.001211089,0.001508267,0.01305285,0.007986264,0.02692949,0.00476887,0.003297108,0.005113326],"category_scores_gemma":[0.2886644,0.001381546,0.0007673296,0.01138015,0.04171227,0.03509999,0.02092133,0.007755559,0.0008541454],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0136664,"about_ca_system_score_gemma":0.01636032,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004467326,"about_ca_topic_score_gemma":0.003863332,"domain_scores_codex":[0.7570277,0.2111143,0.006128638,0.007554424,0.01660922,0.00156565],"domain_scores_gemma":[0.4653349,0.4480742,0.01294641,0.04781499,0.02343908,0.002390467],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","study_design_scores_codex":[0.00008751999,0.00006456397,0.001932194,0.00105621,0.00009097419,0.0003078941,0.4040633,0.001834393,0.001957145,0.4631736,0.007190738,0.1182415],"study_design_scores_gemma":[0.00004582282,0.00007150746,0.002068485,0.004284828,0.00005859005,0.000249063,0.1450165,0.01308055,0.004654824,0.6626827,0.1676261,0.0001610002],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06458036,0.004693317,0.8018883,0.05717623,0.001328643,0.001578596,0.0007860201,0.001212373,0.06675611],"genre_scores_gemma":[0.6886786,0.002484632,0.296264,0.00196785,0.0004993356,0.002352512,0.0005796658,0.001111694,0.006061756],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.1964737,"threshold_uncertainty_score":0.9908909,"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."}}