{"id":"W4404856684","doi":"10.1177/14614456241298915","title":"Topic modelling is a means to an end: On topic modelling in corpus linguistics and discourse analysis","year":2024,"lang":"en","type":"article","venue":"Discourse Studies","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Corpus linguistics; Linguistics; Discourse analysis; Applied linguistics; Computer science; Quantitative linguistics; Sociology; Philosophy","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":[0.0007315878,0.0001659512,0.0003831441,0.0004446038,0.0003587902,0.0001605084,0.0001343953,0.00004481905,0.00002916426],"category_scores_gemma":[0.000166845,0.0001398425,0.0001427935,0.001040854,0.0001814888,0.00008074636,0.00006009475,0.000145139,0.000007308844],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009582096,"about_ca_system_score_gemma":0.00008002405,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00218,"about_ca_topic_score_gemma":0.006673075,"domain_scores_codex":[0.998411,0.0001672214,0.0002774734,0.0004591729,0.0004011389,0.0002839657],"domain_scores_gemma":[0.9991614,0.0004025156,0.00003971077,0.0001534528,0.0001245142,0.0001183756],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001055546,0.00007604805,0.002803365,0.00002566238,0.0007142241,0.00003056536,0.1197039,0.6949272,0.000001244105,0.1557657,0.00005258065,0.025889],"study_design_scores_gemma":[0.00009593102,0.00005661064,0.0004051091,0.0001136106,0.0008236514,1.501714e-7,0.0416992,0.9079748,0.000007223931,0.04343675,0.005094069,0.0002928775],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7687383,0.006117474,0.2108027,0.005374985,0.0007516451,0.0002586155,0.00003284843,0.0001022478,0.007821159],"genre_scores_gemma":[0.9903514,0.0008098888,0.006371479,0.0001633139,0.0005531967,0.0000181159,0.000006313404,0.00001035787,0.001715961],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.221613,"threshold_uncertainty_score":0.5702612,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1362974815568709,"score_gpt":0.4772390681758816,"score_spread":0.3409415866190106,"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."}}