ARCHIVES

Migrants face significant challenges in accessing career guidance due to language barriers, cultural differences, and unfamiliarity with local labor markets. This scoping review synthesizes existing literature on AI-driven conversational models designed to address these challenges and support migrant labor market integration. By analyzing key themes including natural language processing (NLP), real-time knowledge integration, personalized recommendations, user-centered design, and ethical considerations the review identifies essential technical, usability, and ethical requirements for developing effective AI-driven career guidance models. Key findings highlight the necessity of multilingual NLP, contextual awareness, and adaptive machine learning models for personalized support, alongside user-focused features such as cultural sensitivity, intuitive interfaces, and psychometric assessments. Ethical considerations, including bias mitigation, transparency, and data privacy, are critical for building trust and ensuring fairness. The review underscores the interplay between these factors, presenting a comprehensive framework for future AI-driven career guidance solutions. It also offers actionable insights for researchers and developers to create technically sophisticated and socially responsible models, , ultimately empowering migrants to navigate career pathways and achieve sustainable economic integration.