{"id":"W2022913092","doi":"10.1007/s11135-013-9919-0","title":"On the choice of measures of reliability and validity in the content-analysis of texts","year":2013,"lang":"en","type":"article","venue":"Quality & Quantity","topic":"Reliability and Agreement in Measurement","field":"Decision Sciences","cited_by":61,"is_retracted":false,"has_abstract":false,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Reliability (semiconductor); Rhetorical question; Interpretation (philosophy); Reading comprehension; Complement (music); Reading (process); Kappa; Computer science; Measure (data warehouse); Content (measure theory); Psychology; Natural language processing; Content validity; Comprehension; Linguistics; Statistics; Social psychology; Cognitive psychology; Mathematics; Psychometrics; Data mining; 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":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04846977,0.0001511311,0.000825978,0.0001943807,0.0001007961,0.00006156922,0.001148752,0.0000835285,0.0004174048],"category_scores_gemma":[0.03930073,0.00006999595,0.00040318,0.001591698,0.0007542975,0.0001974649,0.0001229438,0.0002251109,0.00001167729],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002848448,"about_ca_system_score_gemma":0.00004681244,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01672968,"about_ca_topic_score_gemma":0.004504059,"domain_scores_codex":[0.9890718,0.00519361,0.001951117,0.0004576677,0.003132679,0.0001931365],"domain_scores_gemma":[0.9763601,0.01916376,0.001126609,0.002017598,0.001278828,0.00005305616],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00005679812,0.0006928099,0.9720294,0.00004776779,0.0001313018,6.744084e-8,0.001274483,0.0002717421,0.003363539,0.0199721,0.0006180998,0.001541912],"study_design_scores_gemma":[0.000191868,0.0001277928,0.9583821,0.00002055731,0.0001301091,4.047712e-8,0.001875709,0.0004187029,0.002590917,0.03605396,0.0001333665,0.00007483747],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9949781,0.0000858313,0.0003830842,0.003135792,0.00007052761,0.0006311501,0.00005094063,0.000004376049,0.0006602306],"genre_scores_gemma":[0.999601,0.00002178792,0.00007083907,0.0002471567,0.000007917351,0.00001809591,0.00000143766,0.000002375308,0.00002936979],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01608186,"threshold_uncertainty_score":0.989818,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.6107004055274742,"score_gpt":0.4566016238261046,"score_spread":0.1540987817013695,"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."}}