{"id":"W2973402705","doi":"10.5539/mas.v13n10p26","title":"Scaled Pearson’s Correlation Coefficient for Evaluating Text Similarity Measures","year":2019,"lang":"en","type":"article","venue":"Modern Applied Science","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Pearson product-moment correlation coefficient; Similarity (geometry); Correlation; Correlation coefficient; Outlier; Metric (unit); Statistics; Mathematics; Spearman's rank correlation coefficient; Computer science; Artificial intelligence","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":[],"consensus_categories":[],"category_scores_codex":[0.01151736,0.001176081,0.001282684,0.01514751,0.0008253657,0.002608233,0.001184606,0.001258452,0.00400707],"category_scores_gemma":[0.09467954,0.0002443036,0.00113103,0.01856358,0.001059268,0.002915512,0.001351445,0.001152027,0.00219323],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009566001,"about_ca_system_score_gemma":0.001405941,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002194523,"about_ca_topic_score_gemma":0.002944452,"domain_scores_codex":[0.9747534,0.00808569,0.003917849,0.003334537,0.009454473,0.0004539459],"domain_scores_gemma":[0.9254867,0.04740373,0.007180631,0.005493858,0.01357665,0.0008583741],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0008350976,0.0003861813,0.1910835,0.003238865,0.002200097,0.0007841478,0.002085614,0.03630426,0.01365025,0.02622399,0.03958389,0.6836241],"study_design_scores_gemma":[0.0001633869,0.002547872,0.28798,0.0009871408,0.0008597286,0.002677573,0.004503324,0.5087348,0.02284962,0.06836978,0.09961668,0.0007102098],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2138575,0.008497422,0.7381066,0.0007281249,0.001050493,0.001437487,0.01396882,0.003770221,0.01858342],"genre_scores_gemma":[0.7126031,0.001440625,0.2712833,0.0001626655,0.0002971312,0.001488121,0.00985497,0.0004321593,0.002437918],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01514751,"threshold_uncertainty_score":0.06091034,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03021596462251229,"score_gpt":0.3165010133162091,"score_spread":0.2862850486936968,"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."}}