JISARA

Abstract: This systematic review synthesizes advances in AI-driven job interview systems, examining their technological foundations, pedagogical alignment, and effectiveness in supporting professional skill development. Existing platforms range from rule-based and NLP-enhanced systems to immersive VR/AR and avatar-based simulations. Recent progress in large language models (LLMs), multimodal feedback, and photorealistic virtual agents has significantly improved adaptivity, realism, and user engagement. However, current systems remain fragmented, with most focusing on either technical or behavioral skills, offering limited emotional responsiveness, insufficient curriculum alignment, and minimal support for integrated coding environments or plagiarism-aware assessments. By analyzing 44 high-quality studies, this review identifies critical gaps in personalization, real-time multimodal evaluation, and pedagogically structured feedback. It proposes a unified framework incorporating emotionally adaptive avatars, interactive coding simulations, domain-aware questioning, and learner-centered dashboards. This work provides the first systematic integration of technical, behavioral, and immersive dimensions of AI-based interview systems, establishing a foundation for designing intelligent, inclusive, and context-aware platforms that better align academic preparation with real-world hiring expectations.

Download this article: JISARA - V19 N3 Page 50.pdf

Recommended Citation: Sanjana, S., Li, Y., He, S., (2026). AI-Enhanced Interview Preparation: A Comprehensive Review of Technical, Behavioral, and Immersive Training Systems. Journal of Information Systems Applied Research and Analytics 19(3) pp 50-67. https://doi.org/10.62273/GJOI3460