TY - GEN
T1 - A Review of Data Augmentation and Data Generation Using Artificial Intelligence in Education
AU - Chui, Kwok Tai
AU - Lee, Lap Kei
AU - Wang, Fu Lee
AU - Cheung, Simon K.S.
AU - Wong, Leung Pun
N1 - Publisher Copyright:
© 2024, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
PY - 2024
Y1 - 2024
N2 - Technological advancement of artificial intelligence enhances the quality of education. Sufficient and high-quality data are important elements in building accurate artificial intelligence models. The real-world scenarios are often small-scale, attributable to various reasons, such as the high cost of data collection, low occurrence of events, protected data, privacy issues, and ethical issues. Data augmentation and generation provide additional training data to facilitate machine learning model construction. This paper reviewed 202 publications to analyze the methodologies, results, and applications of data synthesis approaches for educational research in 2010–2023 (up to August 2023). Basic characteristics were studied, including the number of annual publications, subject areas of publications, top ten publishers, and a word cloud of keywords. It was followed by an in-depth discussion of the top ten most cited publications. Several open challenges and suggestions for potential future research directions were considered.
AB - Technological advancement of artificial intelligence enhances the quality of education. Sufficient and high-quality data are important elements in building accurate artificial intelligence models. The real-world scenarios are often small-scale, attributable to various reasons, such as the high cost of data collection, low occurrence of events, protected data, privacy issues, and ethical issues. Data augmentation and generation provide additional training data to facilitate machine learning model construction. This paper reviewed 202 publications to analyze the methodologies, results, and applications of data synthesis approaches for educational research in 2010–2023 (up to August 2023). Basic characteristics were studied, including the number of annual publications, subject areas of publications, top ten publishers, and a word cloud of keywords. It was followed by an in-depth discussion of the top ten most cited publications. Several open challenges and suggestions for potential future research directions were considered.
KW - artificial intelligence
KW - data augmentation
KW - data generation
KW - small-scale dataset
KW - smart education
UR - http://www.scopus.com/inward/record.url?scp=85177190692&partnerID=8YFLogxK
U2 - 10.1007/978-981-99-8255-4_21
DO - 10.1007/978-981-99-8255-4_21
M3 - Conference contribution
AN - SCOPUS:85177190692
SN - 9789819982547
T3 - Communications in Computer and Information Science
SP - 242
EP - 253
BT - Technology in Education. Innovative Practices for the New Normal - 6th International Conference on Technology in Education, ICTE 2023, Proceedings
A2 - Cheung, Simon K.S.
A2 - Wang, Fu Lee
A2 - Li, Kam Cheong
A2 - Paoprasert, Naraphorn
A2 - Charnsethikul, Peerayuth
A2 - Phusavat, Kongkiti
T2 - 6th International Conference on Technology in Education, ICTE 2023
Y2 - 19 December 2023 through 21 December 2023
ER -