Artificial Intelligence in Educational Technology: A Systematic Review of Datasets and Applications

Abstract

Artificial Intelligence (AI) has the potential to impact a diverse range of domains. For instance, AI for the education domain has received increasing interest with various applications, including predicting performance, curating learning materials, and automated assessment and feedback. Despite the developments, some imbalances appear in the literature; for example, traditional classrooms and non-scientific academic subjects received little attention. This survey provides a systematic review of the current trends in AI research for education, specifically addressing applications within secondary education (ages 11+) through to higher education (HE), and offers a detailed compilation of datasets and methods, facilitating a deeper understanding of the field and encouraging further investigation. It includes a thorough review of the datasets available to encourage and enable future research, development, and collaboration, as well as the establishment of performance benchmarks. Furthermore, this survey provides an overview of issues and problems arising from recent developments, which may aid policymakers in their decision-making and addressing ethical concerns and standards. For example, many AI in Education (AIEd) platforms are not grounded in educational theory. We also present several guidelines to aid future developments in AIEd, guiding long-term impactful projects and investments.