{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01172059,0.001699831,0.001916755,0.003708265,0.00154009,0.007484136,0.002431617,0.002580125,0.06445571],"category_scores_gemma":[0.05864257,0.001629266,0.001702789,0.005481627,0.003278469,0.005894507,0.002841742,0.007006144,0.0555723],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001844887,"about_ca_system_score_gemma":0.00438906,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001524363,"about_ca_topic_score_gemma":0.002123379,"domain_scores_codex":[0.9873067,0.0052885,0.000865693,0.001493123,0.004838202,0.0002078066],"domain_scores_gemma":[0.9307641,0.05503219,0.002086204,0.003871279,0.00743128,0.0008149998],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00003777063,0.00003823255,0.0002751281,0.001868344,0.00006893704,0.000148556,0.001137055,0.0008549988,0.0008866708,0.06113493,0.7370025,0.1965469],"study_design_scores_gemma":[0.00001079762,0.00002918734,0.0004812434,0.000961409,0.00001475595,0.0002363721,0.0002231536,0.0008364388,0.000409507,0.04360657,0.9531399,0.00005072041],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001375159,0.05206118,0.6707836,0.0520248,0.01707586,0.001527367,0.01493846,0.02053362,0.16968],"genre_scores_gemma":[0.01332305,0.05780574,0.6842819,0.02007386,0.01222523,0.005093938,0.01293287,0.02628453,0.1679789],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9882794,"threshold_uncertainty_score":0.2156259,"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."}}