Retyana Wahrini

Retyana Wahrini

Auto-generated profile, based on publicly available information

Retyana Wahrini

Department of Electronic Engineering Makassar South Sulawesi Universitas Negeri Makassar

Research Focus & Metrics

Academic Career Length

1Year (2026-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
25 September 2026 in F1000Research
Verified
Journal Article
Open access
PDF file
ENErvi Novitasari
Ervi Novitasari
KRKhaidir Rahman
Khaidir Rahman
AKAditya Lapu Kalua
Aditya Lapu Kalua
HVHariestya Viareco
Hariestya Viareco
ELEma Lestari
Ema Lestari
RWRetyana Wahrini
Retyana Wahrini
Background Vocational education increasingly requires the integration of artificial intelligence-supported learning and sustainability competencies to prepare students for technology-intensive and environmentally responsible workplaces. However, limited empirical evidence exists on learning ecosystems that combine explainable artificial intelligence, sustainability oriented competency development, and workforce readiness. This study developed and examined an Explainable Green Artificial Intelligence Ecosystem for sustainable vocational education. Methods A sequential explanatory mixed-methods design was employed with 236 vocational students assigned to experimental (n = 118) and control (n = 118) groups. The quantitative phase used a non-equivalent control group pretest posttest quasi experimental design, Partial Least Squares Structural Equation Modeling, Random Forest, Extreme Gradient Boosting, and SHapley Additive exPlanations analysis. Semi-structured interviews were subsequently conducted and analyzed thematically to contextualize the quantitative findings. Results Students receiving the Explainable Green Artificial Intelligence Ecosystem demonstrated greater improvements than those receiving conventional instruction. The experimental group showed large effect sizes for workforce readiness (t = 15.872; d = 1.41), green competencies (t = 14.629; d = 1.36), learning engagement (t = 16.204; d = 1.53), and artificial intelligence literacy (t = 15.311; d = 1.44). Green competencies were the strongest structural predictor of workforce readiness (β = 0.618, p < 0.001). Extreme Gradient Boosting achieved the strongest predictive performance (accuracy = 0.914; R 2 = 0.846), while explainability analysis identified green competencies, learning engagement, and artificial intelligence literacy as the leading predictors of workforce readiness. Qualitative findings indicated improved perceptions of artificial intelligence transparency, adaptive learning, sustainability awareness, human artificial intelligence collaboration, and workforce preparedness. Conclusions The Explainable Green Artificial Intelligence Ecosystem was associated with improved sustainability-oriented competencies and workforce readiness in vocational education. The findings indicate that combining explainable artificial intelligence-supported learning with green competency development may support preparation for sustainable and technology-integrated workplaces.

8 September 2026 in F1000Research
Verified
Journal Article
Open access
PDF file
HHHasbi Hasbi
Hasbi Hasbi
ESEdy Supriyadi
Edy Supriyadi
VHValentinus Lilik Hariyanto
Valentinus Lilik Hariyanto
MNMuhammad Nuruzzaman
Muhammad Nuruzzaman
NNNuzulul Alifin Nur
Nuzulul Alifin Nur
WRWahrini Retyana
Wahrini Retyana
Vocational education needs to adapt to the digitalization and sustainability challenges by introducing innovative learning models that combine flexibility, technology, and sustainability skills. Hybrid Flexible (HyFlex) learning has proven to be a successful model, but its potential in developing Green skills, occupational health and safety (OHS) competence and environmental sustainability awareness is yet to be thoroughly investigated, especially in the realm of smart learning ecosystems. This study used a sequential explanatory mixed methods design. Quantitative phase, a survey was conducted on 172 vocational education students who were analyzed using Partial Least Square Structural Equation Model (PLS-SEM) to test the relationship between HyFlex learning, smart learning ecosystem, learning engagement, and sustainability related outcomes. The qualitative phase involved using semi-structured interviews and focus group discussions to interpret and elaborate on the quantitative results, based on thematic analysis. The results show that the smart learning ecosystem (β = 0.68, p < 0.001) and learning engagement (β = 0.52, p < 0.001) are significant positive factors of HyFlex learning. Smart learning ecosystem and learning engagement, in turn, have a significant impact on green skills, OHS competence, and awareness of environmental sustainability. The direct impacts of HyFlex learning on outcomes related to sustainability, however, are relatively smaller and indicate that the impact of HyFlex learning is channelled through the smart learning ecosystem and learning engagement. Qualitative results also indicate that digital readiness, instructional design and hands-on learning practices are important determinants in the effectiveness of implementing HyFlex. This research shows that HyFlex learning is not enough to train learners on sustainability competency without the presence of a strong smart learning ecosystem and active participation of learners. The results show the need to combine technological infrastructure, pedagogical design and the incorporation of concepts related to sustainability learning approaches to improve the results of vocational education.