View Item 

Challenges of big data in educational assessment

Access Status
Fulltext not available
Authors
Gibson, D.
Webb, M.
Ifenthaler, Dirk
Date
2015
Type
Conference Paper

Metadata
Show full item record
Citation
Gibson, D. and Webb, M. and Ifenthaler, D. 2015. Challenges of big data in educational assessment, in Sampson, D. and Spector, J.M. and Ifenthaler, D. and Isaias, P. (ed), Proceedings of the 12th International Conference on Cognition and Exploratory Learning in the Digital Age, CELDA 2015, Oct 24-26 2015, pp. 92-100. Maynooth, Greater Dublin, Irleand: CELDA.
Source Title
Proceedings of the 12th International Conference on Cognition and Exploratory Learning in the Digital Age, CELDA 2015
ISBN
School
DVC Education
URI
Collection
Abstract

This paper briefly discusses four measurement challenges of data science or 'big data' in educational assessments that are enabled by technology: 1. Dealing with change over time via time-based data. 2. How a digital performance space's relationships interact with learner actions, communications and products. 3. How layers of interpretation are formed from translations of atomistic data into meaningful larger units suitable for making inferences about what someone knows and can do. 4. How to represent the dynamics of interactions between and among learners who are being assessed by their interactions with each other as well as with digital resources and agents in digital performance spaces. Because of the movement from paper-based tests to online learning, and in order to make progress on these challenges, the authors advocate the restructuring of training of the next generation of researchers and psychometricians to specialize in data science in technology enabled assessments. This call to action stemmed from discussions at EDUsummIT 2013, which will be published in depth in a special issue of Education and Information Technologies.