Affiliation:
1. Institute for Intelligent Systems University of Memphis Memphis Tennessee USA
2. Research Educational Testing Service Princeton New Jersey USA
Abstract
AbstractWe argue in this paper that there is currently no adequate theoretical framework or model that spans the twelve odd year trajectory from non‐reader to proficient reader, nor addresses fine‐grain skill acquisition, mastery and integration. The target construct itself, reading proficiency, as often operationalized as an endpoint of formal secondary schooling, is defined and measured in imprecise, fragmented terms. Consequently, schools (and empirical research) fall back on heuristics like the Simple View of Reading, or a few stages (learn to read, read to learn, read to do) to describe reading development. Those models, however, are too general to guide instructional decisions for adaptive learning systems. Progress in engineering an adequate learning system has been inhibited by a mismatch with curriculum standards and school organization that impose good‐faith but not fully optimized developmental targets on the educational system. We propose the development of a learning and assessment framework to scaffold reading proficiency development while accounting for the diverse learning trajectories of groups or individuals across development. We then identify some key problems, challenges and opportunities that AI technologies are poised to help us address in conceiving individualized, adaptive learning systems for reading proficiency across the developmental spectrum. We close with a selective review of examples of AI‐enhanced research or products.
Practitioner notesWhat is already known about this topic
Reading proficiency is a vital component of education systems design.
Theoretical and empirical studies across multiple disciplines have been published, but much of this research is framed in fragmented theories that do not seamlessly span the trajectory of life‐long reading development.
Current assessments are time‐consuming, coarse‐grained and fail to provide a roadmap for educators and designers of adaptive learning environments.
There is a significant lack of knowledge of potentially non‐linear growth in reading skills within or between years and how to design adaptive instruction for diverse subpopulations.
What this paper adds
We describe the initial steps towards a literacy learning and assessment framework that spans the trajectory from non‐reader to proficient reader.
We provide a landscape of exemplars of artificial intelligence and computational linguistics that reflect the possibilities of a more comprehensive, cohesive literacy development system.
We reflect upon key problems, challenges and opportunities that AI technologies can help address in conceiving individualized, adaptive learning systems for reading proficiency across the developmental spectrum.
Implications for practice and/or policy
AI and computational linguistics can help fill in the gaps in understanding and enacting a longitudinal vision of reading development.
Educators would ideally know what to expect of their students at particular points of development, identify deviations and have additional tools to intervene effectively to maximize progress.
There is a need to develop adaptive instruction that spans the development of proficiency from preschool to college/career levels and adapts to address common barriers among diverse subpopulations.
Cited by
2 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献