Um estudo comparativo entre dois modelos que estimam a habilidade dos estudantes: ELO e Teoria de Resposta ao Item

Resumo

Currently, there are many online platforms that offers programming exercise libraries where evaluation occurs automatically. The present work presents an analysis of two models that aims to estimate the students' ability: ELO and TRI Theory. ELO was developed to classify players through game history, and TRI estimates skill through a set of responses given to a set of items. For the application of the models we use a database made available by an Online Judge platform. The results show us differences between the models in relation to the estimated abilities, differences that we believe are related to the way in which each model estimates the parameters.