{"id":"W4400355843","doi":"10.1007/s11135-024-01933-7","title":"On measurement of distances between texts in dictionary-based content analysis","year":2024,"lang":"en","type":"article","venue":"Quality & Quantity","topic":"Lexicography and Language Studies","field":"Arts and Humanities","cited_by":4,"is_retracted":false,"has_abstract":false,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Content (measure theory); Natural language processing; Content analysis; Computer science; Information retrieval; Statistics; Mathematics; Sociology; Social science","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":[0.0008888477,0.0001155048,0.0003259463,0.0002920027,0.0001230078,0.00006807513,0.00008770313,0.00002572546,0.0004348121],"category_scores_gemma":[0.00005987392,0.00008719259,0.0003086643,0.0002528871,0.0002359984,0.00009356457,0.00001323278,0.0001139421,0.0000113868],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005108658,"about_ca_system_score_gemma":0.00002802668,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005898795,"about_ca_topic_score_gemma":0.04417311,"domain_scores_codex":[0.9985912,0.0001658867,0.0004068803,0.0002252659,0.0004728456,0.0001378543],"domain_scores_gemma":[0.9993806,0.0002302596,0.00007704089,0.0001729274,0.0001119978,0.00002715576],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.00008412605,0.0003537458,0.1904441,0.0004501035,0.001520595,0.000008120461,0.01850553,0.00004586581,0.00004889349,0.7855273,0.00049353,0.002518089],"study_design_scores_gemma":[0.0007706501,0.0004166798,0.9407205,0.0006267243,0.001101643,4.8855e-8,0.01155158,0.0001857362,0.0008495322,0.008898756,0.03429807,0.0005801102],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9877727,0.002707586,0.0006011464,0.0004699838,0.0002581457,0.0001317887,0.0003721381,0.00007831992,0.0076082],"genre_scores_gemma":[0.999641,0.00001545127,0.00001243009,0.00007405924,0.0001029426,0.0000129794,0.00002765889,0.000005041476,0.0001084507],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7766286,"threshold_uncertainty_score":0.9732683,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.233178348508226,"score_gpt":0.3480554124898039,"score_spread":0.1148770639815779,"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."}}