{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.007217741,0.0007878228,0.0009832386,0.0116708,0.001269692,0.003513515,0.00137899,0.00113274,0.002475184],"category_scores_gemma":[0.06822502,0.0004278796,0.0008015778,0.01218234,0.002123939,0.005670712,0.003718247,0.001130324,0.001240023],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001067176,"about_ca_system_score_gemma":0.001280682,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005439012,"about_ca_topic_score_gemma":0.006471321,"domain_scores_codex":[0.9848217,0.008187843,0.001097286,0.001992197,0.00357342,0.0003275018],"domain_scores_gemma":[0.9247911,0.06137855,0.00272985,0.004267832,0.006224012,0.0006086826],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001118464,0.0002619937,0.03557256,0.001349698,0.0005553197,0.0002023413,0.004906972,0.02131126,0.03641766,0.03864785,0.002878087,0.8567777],"study_design_scores_gemma":[0.0002021641,0.001126336,0.1229225,0.0007315798,0.0006354393,0.001268819,0.008085997,0.6508153,0.05445758,0.1363715,0.0229141,0.0004686309],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1410922,0.001917721,0.8468915,0.0003555742,0.000118061,0.0003021382,0.001196198,0.0007903186,0.00733637],"genre_scores_gemma":[0.4905767,0.000822105,0.5045044,0.00007339521,0.00008517064,0.0002742782,0.001883271,0.0003121137,0.001468442],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9927822,"threshold_uncertainty_score":0.03817147,"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."}}