Concept information
Terme préférentiel
Cohen's kappa
Définition
- A statistic used to assess the effectiveness of machine learning classification models. ( https://bootcamp.uxdesign.cc/cohens-kappa-score-33a0710b2fe0)
Concept générique
Synonyme(s)
- Cohen's kappa coefficient
- Cohen's Kappa score
Contexte(s) définitoire(s)
- Cohen's kappa coefficient is a statistic that is used to measure inter-rater reliability for categorical items. (Jamali, Yaghoobzadeh & Faili, 2022)
Exemple
- Cohen's Kappa scores (Cohen 1960) for POS tags and dependency labels in all evaluation conditions are above 0.96. (Berzak, Kenney, Spadine, Wang, Lam, Mori, Garza & Katz, 2016)
- Note that computing Cohen's Kappa here is somewhat artificial as in the real world there is an (almost) unlimited space of possible Wikipedia identifiers. (Lin & Zeldes, 2021)
- The Cohen's kappa coefficients are above 0.7 indicating a high correlation and agreement between the two human annotators. (Li, Zhao, Wen & Song, 2019)
- To evaluate the annotator's performance on this task we evaluate the inter-annotator agreement (IAA) for each of the 13 topics using Cohen's Kappa (CK) score. (Dalal, Srivastava & Singh, 2023)
- We computed the inter-annotator agreement in terms of Cohen's Kappa (κ) score (Cohen 1960) to check the validity. (Hossain, Sharif, Hoque & Preum, 2024)
Traductions
-
français
-
coefficient de kappa
-
coefficient Kappa
-
coefficient Kappa de Cohen
-
méthode du Kappa
-
κ de Cohen
URI
http://data.loterre.fr/ark:/67375/8LP-N657SLSC-M
{{label}}
{{#each values }} {{! loop through ConceptPropertyValue objects }}
{{#if prefLabel }}
{{/if}}
{{/each}}
{{#if notation }}{{ notation }} {{/if}}{{ prefLabel }}
{{#ifDifferentLabelLang lang }} ({{ lang }}){{/ifDifferentLabelLang}}
{{#if vocabName }}
{{ vocabName }}
{{/if}}