{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.541793,0.002545875,0.008126822,0.01661878,0.005150335,0.02090329,0.009393757,0.01458731,0.002089737],"category_scores_gemma":[0.7980718,0.002844259,0.005209146,0.01394614,0.02571153,0.02689298,0.01054025,0.0145451,0.001330598],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.009846215,"about_ca_system_score_gemma":0.01226202,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004079759,"about_ca_topic_score_gemma":0.004716741,"domain_scores_codex":[0.3475615,0.5517341,0.03599764,0.01454016,0.04803233,0.002134253],"domain_scores_gemma":[0.0711372,0.8797029,0.007860939,0.01708987,0.02320761,0.001001566],"domain_codex":"methods","domain_gemma":"methods","domain_candidate":"methods","domain_consensus":"methods","study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.002185821,0.0006913263,0.02868072,0.004095567,0.002842804,0.0004190354,0.01870241,0.006566782,0.00353463,0.6692401,0.008258676,0.2547823],"study_design_scores_gemma":[0.0008728753,0.001227992,0.03435435,0.008274422,0.001130663,0.0007761896,0.008267,0.06552855,0.006247818,0.8629308,0.009479401,0.0009099682],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.08002254,0.0118908,0.8504657,0.02699562,0.001070525,0.003429642,0.001058546,0.0005415359,0.02452511],"genre_scores_gemma":[0.4610806,0.003294003,0.5245227,0.002612823,0.0008772577,0.005605782,0.0005927028,0.0003572896,0.001056797],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.458207,"threshold_uncertainty_score":0.5650508,"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."}}