AI-Based Mock Interview Evaluator: An Emotion and Confidence Classifier Model

Abstract

This research focuses on developing an AI-based mock interview evaluator that analyzes candidate emotions and confidence levels. The system leverages computer vision and natural language processing to process video and audio data from mock interviews. Through a multi-modal approach, it classifies emotional states (e.g., nervousness, excitement, confidence) and assesses overall confidence levels. The developed system demonstrates improved accuracy over existing methods, providing valuable feedback to candidates for enhancing their interview performance. This contributes to the field by offering a more comprehensive and objective assessment tool for interview preparation.

Introduction

Effective interviewing skills are crucial for career success. However, current methods for assessing interview performance often rely on subjective human judgment, leading to inconsistencies and biases. This lack of objectivity creates a need for a more standardized and reliable evaluation process. This research addresses this gap by developing an AI-powered system that provides objective feedback on a candidate's emotional state and confidence during a mock interview. This allows candidates to identify areas for improvement, leading to better interview performance and ultimately increasing their chances of securing desired positions. The challenge lies in accurately and reliably classifying subtle emotional expressions and confidence cues from multimodal data.

Objectives

• Develop an accurate AI model for classifying emotions during mock interviews.
• Create a reliable system for assessing interviewee confidence levels.
• Design a user-friendly interface for providing constructive feedback to candidates.