Combinatorial and Psychometric Methods for Game-Based Assessment.

Saved in:

Bibliographic Details
Title:	Combinatorial and Psychometric Methods for Game-Based Assessment.
Authors:	Kickmeier-Rust, Michael¹ michael.kickmeier@phsg.ch
Source:	Proceedings of the European Conference on Games Based Learning. 2018, p299-306. 8p.
Subject Terms:	Video games in education, Video games, Machine learning, Factor analysis, Psychometrics
Abstract:	Assessing competencies and learning progress is a vital task for digital learning games. Specifically, the adaptation and personalization of gaming and learning activities, which is considered one of key features to assure appropriate learning, requires a robust and theory grounded assessment. This establishes a basis for the game, as an autonomous entity, to gain a certain level of understanding of the individual learners / players. A second aspect in the context of game-based assessment is assessment with games. Over the past years, digital games have been identified as an ideal vehicle to assess various types of aptitude (such as competencies) but also further characteristics such as personality traits. Val Shute, in her influential work, often argues that assessment and personalization is often too simplified, abstract, and decontextualized to suit the needs of successful individual learning support. In this contribution, I want to highlight the links of game-based assessment to techniques of Learning Analytics and psychometric methodologies. I present a combinatorial, structural approach to the measurement of competencies and individual learning paths based on Knowledge Space Theory, extended by Micro Adaptivity, a well-elaborated approach to learner modelling and in-game adaptation. I complement the ideas of structural assessment models with psychometric considerations, in particular the aspects of assessment accuracy, reliability, and validity. The idea is to capitalize on the methodological accuracy of Item Response Theory scaling, where a number of items are arranged on a linear dimension of "difficulty" and improve the accuracy of the multi-dimensional micro adaptive assessment models. [ABSTRACT FROM AUTHOR]
	Copyright of Proceedings of the European Conference on Games Based Learning is the property of Academic Conferences & Publishing International Ltd. and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database:	Education Research Complete

Description
Abstract:	Assessing competencies and learning progress is a vital task for digital learning games. Specifically, the adaptation and personalization of gaming and learning activities, which is considered one of key features to assure appropriate learning, requires a robust and theory grounded assessment. This establishes a basis for the game, as an autonomous entity, to gain a certain level of understanding of the individual learners / players. A second aspect in the context of game-based assessment is assessment with games. Over the past years, digital games have been identified as an ideal vehicle to assess various types of aptitude (such as competencies) but also further characteristics such as personality traits. Val Shute, in her influential work, often argues that assessment and personalization is often too simplified, abstract, and decontextualized to suit the needs of successful individual learning support. In this contribution, I want to highlight the links of game-based assessment to techniques of Learning Analytics and psychometric methodologies. I present a combinatorial, structural approach to the measurement of competencies and individual learning paths based on Knowledge Space Theory, extended by Micro Adaptivity, a well-elaborated approach to learner modelling and in-game adaptation. I complement the ideas of structural assessment models with psychometric considerations, in particular the aspects of assessment accuracy, reliability, and validity. The idea is to capitalize on the methodological accuracy of Item Response Theory scaling, where a number of items are arranged on a linear dimension of "difficulty" and improve the accuracy of the multi-dimensional micro adaptive assessment models. [ABSTRACT FROM AUTHOR]
ISSN:	20490992