Transforming Education With Large Language Models: Trends, Themes, and Untapped Potential
Our research focuses on the transformative intersection of Large Language Models (LLMs) and education in the last six years (2019–2024), examining their potential to modernize educational systems and enhance learning outcomes. Leveraging a comprehensive methodological framework, we analyz...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/11006075/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Our research focuses on the transformative intersection of Large Language Models (LLMs) and education in the last six years (2019–2024), examining their potential to modernize educational systems and enhance learning outcomes. Leveraging a comprehensive methodological framework, we analyzed 9,598 publications from Web of Science (WoS), extracting 25,381 education-related terms and mapping academic trends across diverse research areas. Educational research involving LLMs focuses heavily on learning, research and training, with terms such as “education” (1546), “learning” (4828), “research” (4438) and “training” (327) frequently appearing in the analyzed dataset. Specific applications such as grading (121) and tutoring (82) are less emphasized, presenting potential areas for further exploration. Key elements include annual publication patterns, institutional collaborations, citation dynamics and keyword co-occurrence maps. Advanced topic modeling techniques, such as LDA, LDA-BERT and BERT-Clustering, reveal a spectrum of themes, from foundational AI concepts in education to domain-specific applications in fields like legal and financial contexts. The findings highlight major educational themes such as “AI in education”, “medical education” and “programming education”, alongside subfields like “computer science education” and “software engineering education” underscoring a strong focus on technology-driven learning. |
|---|---|
| ISSN: | 2169-3536 |