Application and theory gaps during the rise of Artificial Intelligence in Education

Abstract Considering the increasing importance of Artificial Intelligence in Education (AIEd) and the absence of a comprehensive review on it, this research aims to conduct a comprehensive and systematic review of influential AIEd studies. We analyzed 45 articles in terms of annual distribution, leading journals, institutions, countries/regions, the most frequently used terms, as well as theories and technologies adopted. We also evaluated definitions of AIEd from broad and narrow perspectives and clarified the relationship among AIEd, Educational Data Mining, Computer-Based Education, and Learning Analytics. Results indicated that: 1) there was a continuingly increasing interest in and impact of AIEd research; 2) little work had been conducted to bring deep learning technologies into educational contexts; 3) traditional AI technologies, such as natural language processing were commonly adopted in educational contexts, while more advanced techniques were rarely adopted, 4) there was a lack of studies that both employ AI technologies and engage deeply with educational theories. Findings suggested scholars to 1) seek the potential of applying AI in physical classroom settings; 2) spare efforts to recognize detailed entailment relationships between learners’ answers and the desired conceptual understanding within intelligent tutoring systems; 3) pay more attention to the adoption of advanced deep learning algorithms such as generative adversarial network and deep neural network; 4) seek the potential of NLP in promoting precision or personalized education; 5) combine biomedical detection and imaging technologies such as electroencephalogram, and target at issues regarding learners’ during the learning process; and 6) closely incorporate the application of AI technologies with educational theories.