AI-Enabled Automated Interview Evaluation System

Authors: Vaibhavi Kabade, Gayatri Patil, Shivani Godse, Aayusha Jain, Mayur Kumbharde

Country: India

Full-text Research PDF File:   View   |   Download

Abstract: In today’s competitive job market, evaluating candidates efficiently and objectively is crucial for recruiters. This paper presents the design and mplementation of an AI-enabled Interview Evaluation System that automates candidate assessment through a combination of multiple intelligent modules. It includes MCQ-based technical evaluations, semantic analysis of verbal responses using NLP models, and real-time facial verification via computer vision. The system is built using Flask for backend processing and SQLite as the database, offering a lightweight yet powerful solution for small-to-mid-scale deployment. Verbal answers are evaluated using transformer-based semantic similarity models from the Sentence Transformer library. Webcam-based face validation is performed using OpenCV and Haar Cascade classifiers to detect malicious activity such as impersonation or multiple faces. The system supports both typed and spoken answers, includes PDF report generation, and provides an intuitive admin dashboard. Experimental results demonstrate the model's efficiency and accuracy in scoring responses and maintaining interview integrity.

Keywords: : Interview Bot, Natural Language Processing, Verbal Evaluation, MCQ Assessment, Face Detection, Flask, Sentence Transformer, Haar Cascade.

Paper Id: 232543

Published On: 2025-06-02

Published In: Volume 13, Issue 3, May-June 2025

Share this