Tiny Machine Learning and Edge AI in Technical and Vocational Education: A Hybrid Bibliometric and Systematic Review (2019–2025)
Year: 2026
Type: preprint
Abstract: This pre-registration documents the protocol for a hybrid bibliometric and systematic literature review (SLR) examining the integration of Tiny Machine Learning (TinyML) and Edge Artificial Intelligence (Edge AI) in technical and vocational education and training (TVET). Despite TinyML emerging as a foundational competency for Industry 4.0 workforces, the educational research landscape on TinyML in TVET has not been systematically mapped. This review will (1) map publication trends and intellectual structure (RQ1–RQ2 via bibliometric analysis using VOSviewer and R bibliometrix), (2) synthesize themes, pedagogical approaches, and technologies (RQ3 via thematic SLR following PRISMA 2020 guidelines and Braun & Clarke's reflexive thematic analysis), and (3) identify research gaps relevant to developing-country vocational education contexts (RQ4). Search will be conducted across Scopus, Web of Science, ERIC, and IEEE Xplore. Inter-rater reliability for screening and thematic coding will be measured using Cohen's kappa (target ≥ 0.61). Findings will inform curriculum development, teacher training, and policy recommendations for TVET institutions in developing countries.
Authors: Suhendar Aryadi, Suciati, Suartini, Tuti
Language: English
Subfield: Education
Field: Social Sciences
Domain: Social Sciences
SDG: Quality education
Open Access status: green
OpenAlex ID: W7160743869
