{"id":"W4405356570","doi":"10.5539/ijel.v15n1p71","title":"An Introduction to Quantitative Text Analysis for Linguistics: Reproducible Research Using R","year":2024,"lang":"en","type":"article","venue":"International Journal of English Linguistics","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Linguistics; Applied linguistics; Quantitative analysis (chemistry); Natural language processing; Chemistry; Philosophy; Chromatography","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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.009397797,0.0001032508,0.0002679471,0.001867758,0.0002930438,0.0005898604,0.0005497794,0.00007156931,0.0001087734],"category_scores_gemma":[0.4218689,0.0001009994,0.0002806931,0.00184531,0.0001383427,0.0001002028,0.0000470031,0.0003209686,0.000005128339],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004137613,"about_ca_system_score_gemma":0.0006462466,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000264056,"about_ca_topic_score_gemma":0.0002236345,"domain_scores_codex":[0.9969877,0.0004552407,0.0006435724,0.0003783058,0.001292936,0.0002422742],"domain_scores_gemma":[0.9082126,0.002048956,0.0002080159,0.0001867181,0.08914277,0.0002009332],"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":[0.0001892258,0.0001710874,0.000757557,0.00001624943,0.001840356,0.00002844498,0.01362219,0.1524694,0.00005648372,0.8166172,0.011295,0.002936772],"study_design_scores_gemma":[0.0001023627,0.0001738606,0.0001180963,0.00003659656,0.0004205124,3.584116e-7,0.003460358,0.04059595,0.0001364136,0.02994041,0.9248894,0.0001256585],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02316701,0.001172659,0.8361025,0.002119045,0.1135792,0.0005125682,0.0001465968,0.0001371578,0.02306322],"genre_scores_gemma":[0.7326466,0.00003572611,0.1459039,0.00004683368,0.1209912,0.000003330463,0.00002310291,0.00001799696,0.000331287],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9135944,"threshold_uncertainty_score":0.5830009,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1673412948728796,"score_gpt":0.5322337886602312,"score_spread":0.3648924937873516,"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."}}