Role of AI in Blended Learning: A Systematic Literature Review
Bibliographic record
Abstract
As blended learning moved toward a new phase during the COVID-19 pandemic, advancements in artificial intelligence (AI) technology provided opportunities to develop more diverse and dynamic blended learning. This systematic review focused on publications related to the use of AI applications in blended learning. The original studies from January 2007 to October 2023 were extracted from the Google Scholar, ERIC, and Web of Science databases. Finally, 30 empirical studies under the inclusion criteria were reviewed based on two conceptual frameworks: four key challenges of blended learning and three roles of AI. We found that AI applications have been used mainly for the online asynchronous individual learning component in blended learning; little work has been conducted on AI applications that help connect online activities with classroom-based offline activities. Many studies have identified the role of AI as a direct mediator to help control flexibility and autonomy of students in blended learning. However, abundant studies have also identified AI as a supplementary assistant using advanced learning analytics technologies that promote effective interactions with students and facilitate the learning process. Finally, the fewest number of studies have explored the role of AI as a new subject such as use as pedagogical agents or robots. Considering the advancements of generative AI technologies, we expect more research on AI in blended learning. The findings of this study suggested that future studies should guide teachers and their smart AI partner to implement blended learning more effectively.
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
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 | 0.015 | 0.061 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.005 | 0.005 |
| Bibliometrics | 0.021 | 0.021 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.004 | 0.005 |
| Open science | 0.002 | 0.003 |
| Research integrity | 0.002 | 0.002 |
| Insufficient payload (model declined to judge) | 0.005 | 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, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
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".