On pesonalised multi-agent learning system: learning outcomes assessment agent

Abstract

The paper aims to present a learning outcomes assessment software agent necessary to create an improved personalised multi-agent learning system. First of all, the authors performed systematic literature review on competences-based assessment and e-portfolios application to personalise learning in Clarivate Analytics (formerly Thomson Reuters) Web of Science database. The systematic literature review was performed to answer the following research question: “How competences-based assessment and e-portfolios are applied in intelligent learning systems?” After that, methodology of eportfolios and competence based assessment application in personalised multi-agent learning system is presented. The advantages of the assessment methodology presented are as follows: (1) it motivates students by showing them acquired competences; (2) supports assessment enhanced learning by indicating competences in need of improvement; (3) compiles and preserves competence based portfolio for yearly progress tracking; (4) does not label and compare students to each other with grades; (5) seeks that all students acquire all necessary competences instead of a passing grade; (6) provides assessment sensitive to individual talents of students by eschewing grades and preserving authentic performance evidence in form of portfolio. Finally, the authors present a model of competences-based learning outcomes assessment agent to be used while creating intelligent multiagent learning system. The agent implements the approach to assessment expressed in the methodology and supplements it with additional features such as dynamic notifications about newly acquired competences and sequential assessment activities.