Mapping Artificial Intelligence in Education Research: a Network?based Keyword Analysis

In this study, we review 1830 research articles on artificial intelligence in education (AIED), with the aim of providing a holistic picture knowledge evolution interdisciplinary field from 2010 to 2019. A novel three-step approach analysis keyword co-occurrence networks (KCN) is proposed identify structure, clusters and trending keywords within AIED over time. The results reveal considerable diversity field, centering around two sustained themes: intelligent tutoring systems (2010-19) massive open online courses (since 2014). focal educational concerns reflected are: (1) learning; (2) game-based (3) collaborative (4) assessment; (5) affect; (6) engagement; (7) learning design. highly connected relevant analytic techniques include natural language processing, data mining, analytics machine learning. Neural network, deep learning, eye tracking, personalized are as they have emerged key structural roles latest two-year period analyzed. This first article systematic large body literature education, it uncover underlying patterns connectivity well provide insight into its future development. multi-scale (macro, meso, micro) framework study can also be applied map development other scientific areas.