📄 Abstract
Interviewing performance is a crucial milestone in engineering students' transition into the world of work. Despite having good technical knowledge, students find interviewing an area of difficulty during job placements. Traditionally, interview training involves resource-intensive interviews amongst peers and with professors who can vary in quality of the feedback offered. This paper presents an AI-assisted mock interview system design that uses NLP technologies for resume parsing and response evaluation, and AI for generating dynamically changing questions, specifically to help engineering students overcome their difficulties in preparing for interviews. The system architecture consists of four modules: resume and profile parsing, dynamic question generation, multi-dimensional response evaluation (response content, language skills, and delivery/confidence), and a structured feedback reporting module. These features make up an interview process that is scalable, repeatable, and judgment-free. The literature includes considerable research on developing mock interview systems for general employability and IT graduates. However, we found a gap in incorporating structured evaluation of language proficiency into the interviewing simulation systems, which were designed specifically for engineering students. This paper presents a methodology for designing a single-group pre-test/post-test pilot study to evaluate the effectiveness of our system and to present possible.
🏷️ Keywords
📚 How to Cite:
Tanuja Chundru, Dr.Venkata Ramana Manipatruni , DESIGN AND EVALUATION OF AN AI-BASED MOCK INTERVIEW SYSTEM FOR ENGINEERING STUDENTS USING NLP AND GENERATIVE AI , Volume 12 , Issue 9, September 2026, EPRA International Journal of Multidisciplinary Research (IJMR) , Pages: 305 - 313 ,