Machine Learning–Driven Personalization of Teachers’ Professional Learning Pathways

This study investigates the potential of machine learning algorithms to personalize teachers’ professional learning pathways within the context of data-driven education. The research employed a quantitative, descriptive–correlational design involving ۳۵۰ teachers from public schools in Gorgan, Iran. Data were collected through a structured questionnaire assessing teachers’ technology familiarity, perceived benefits and challenges of digital integration, and professional learning preferences. Descriptive and inferential analyses, including multiple linear regression, were conducted to identify predictors of teachers’ technology familiarity. Results indicated that academic degree, teaching experience, and institutional support significantly predicted technology familiarity, whereas gender showed no significant effect. Teachers reported accessibility and flexibility as key benefits of technology use, alongside challenges such as limited technical knowledge, unreliable internet access, and high costs of digital tools. The study concludes that machine learning–enabled personalization, when ethically governed and contextually adapted, can enhance alignment between teachers’ professional learning needs and institutional objectives. Practical implications highlight the necessity of integrating AI-based recommender systems into national teacher development frameworks to promote equitable, adaptive, and data-informed professional learning ecosystems.

Keywords:

Machine learning , Personalized professional development , Teacher learning pathways , Educational data mining , Ethics in data-driven personalization