Bibliometric Analysis of Potential Themes and Trend Development of ChatGPT in the Field of Education
Bibliographic record
Abstract
The purpose of this article is to review existing research on ChatGPT in education through bibliometric analysis. The research questions are: First, what are the basic characteristics of the research on issues related to ChatGPT in educational applications? Second, what are the main research topics of ChatGPT in educational applications? Third, how has the international topic of ChatGPT in educational applications evolved? The research method is to use VOSviewer and SATI's bibliometric mapping research tools to analyze and visualize the author information and keywords of published articles to observe the basic characteristics, high-frequency research keywords and the evolution trend of the research topic in the field. The expected research contribution is to provide help and reference for researchers in their research in the field of ChatGPT education. The research results reveal several key findings. First, the number of documents published in journals within this research field is on an overall upward trend. Asian scholars and research institutions significantly contribute to the volume of published articles. The region with the highest number of publishing institutions is Asia, specifically Japan. Among the authors of these published articles, Chinese scholars hold the largest proportion, occupying the second and third positions. Second, on an international scale, the primary research topic is Artificial Intelligence. Third, the evolution of ChatGPT's international theme in educational applications has progressed from early scholars' research on ChatGPT school courses to investigations into the performance of artificial intelligence itself. Subsequently, it shifted towards research on ChatGPT medical education and ultimately evolved into studies related to ChatGPT language models and patient education.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Direct model labels (unvalidated)
Per-model category and study-design labels from the labeling rounds. They are machine output, unvalidated, and the disagreement between models ships as data. No study design here is MEDLINE-validated yet.
| Model arm | Categories | Study design | Confidence |
|---|---|---|---|
| gemma | Bibliometrics Domain: not available · Genre: Empirical About the Canadian research system: no · About a Canadian topic: no | Observational | low |
| gpt | Bibliometrics Domain: not available · Genre: Empirical About the Canadian research system: no · About a Canadian topic: no | Observational | high |
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.008 | 0.053 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.126 | 0.169 |
| Science and technology studies | 0.002 | 0.001 |
| Scholarly communication | 0.006 | 0.005 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedLabeled directly by 2 models reading the full record.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".