A Personalized Summative Model based on Learner’s Effort

Abstract

Nowadays, instructors apply a large variety of learning methodologies to help learners to achieve the learning outcomes and to assess the knowledge acquired across the course. Formative and summative assessment models are mainly applied in multiple combinations independently of the learning environment (on-site, online or blended). When we move to an adaptive learning, the adaption tends to be in the learning process (learning path, activities, educational resources) mainly related to formative models but little adaption can be found related to summative models and very restrictive. In the latter case, grade formulas depending on performed assessment activities are typically defined to provide a personalized learning process. In this paper, we introduce the basis of an innovative personalized summative model based on learner's preferences and effort. Although this model conceptually may allow passing a course without evaluating all learning outcomes, it is not far from conventional summative models where a certain grade is required to pass the course and the learner may not have acquired all the knowledge taught in the course. The paper introduces the model and it also analyses an opinion survey on instructors and learners.

Formalizing Logic Based Rules for Skills Classification and Recommendation of Learning Materials

“…In the views of [30] adaptive or personalised learning tends to model learners' learning path, activities and educational resource. To this end, several e-learning recommender systems have been proposed.…”

“…To this end, several e-learning recommender systems have been proposed. In [30] for instance, a standalone quasi-summative assessment model was proposed to boost instruction process and customisation of learning path. In the model, students are graded based on some learning activities using a model of equation, and the adaption on the students' preferences and effort spent on course.…”

A multi-agent approach to adaptive learning using a structured ontology classification system

“…2001;Verbert et al 2012). The stated axioms as implemented are the modelled learning paths (Bañeres, 2017) for individual students for a given desired_Concept. .send(agMaterial, achieve, has_KB(X, delete_select));…”