InterviewBo: Multimodal Intelligence System for End-to-End Recruitment Process Automation and Skill Interpretation

Anandakumar, S.; Mylesh, M.; Elavarasan, G.; Surya, S.; Gomathi, V.

doi:https://doi.org/10.55041/ijcope.v2i4.795

Volume 02, Issue 04

Published on: April 2026

INTERVIEWBO: MULTIMODAL INTELLIGENCE SYSTEM FOR END-TO-END RECRUITMENT PROCESS AUTOMATION AND SKILL INTERPRETATION

S. Anandakumar M. Mylesh G. Elavarasan S. Surya V. Gomathi

Dr.G.Gokula krishnan

Department of Computer Science and Engineering

Jayalakshmi Institute Of Technology

Dharmapuri

DOI:https://doi.org/10.55041/ijcope.v2i4.795

Article Status

Plagiarism Passed Peer Reviewed Open Access

Available Documents

Download PDF Review Report

Abstract

Recruitment preparation has become more demanding as modern hiring processes evaluate not only technical knowledge but also problem-solving ability, academic performance, communication clarity, and domain understanding. Traditional mock interviews, which rely on generic questions and subjective feedback, often fail to provide candidates with clear, personalized insights into their real performance. As a result, many candidates attend actual interviews without knowing their strengths, weaknesses, or the specific areas that need improvement. To address this gap, this project presents an AI-Driven Mock Interview Platform that simulates a realistic interview environment and evaluates candidates through multiple intelligent assessment stages. Sentence-BERT (SBERT) is used for profile analysis, enabling the system to understand resume content, technical skills, project descriptions, completed courses, selected job role, and academic details such as 10th and 12th marks and college CGPA. This contextual understanding helps generate role-specific and profile-relevant interview questions instead of generic ones. Aptitude and cognitive performance are assessed using a Gradient Boosting Classifier (GBC), while coding performance is evaluated through Code2Vec embeddings to analyze program structure and logic from the submitted code. A T5 based question generator enables the HR avatar to ask personalized questions, and candidate answers are evaluated using NLP for relevance, clarity, and understanding. Academic data, skills, aptitude, coding, and interview performance are combined into a final score. Using SHAP for explainability, the system shows how each factor influenced the result, highlights strengths and weaknesses, and recommends suitable courses and job roles to improve career readiness.

Keywords-- Artificial Intelligence (AI), Mock Interview System, Natural Language Processing (NLP), Sentence-BERT (SBERT), Gradient Boosting Classifier (GBC), Code2Vec, Explainable AI (XAI), SHAP, Automated Interview Evaluation.

How to Cite this Paper

Anandakumar, S., Mylesh, M., Elavarasan, G., Surya, S. & Gomathi, V. (2026). InterviewBo: Multimodal Intelligence System for End-to-End Recruitment Process Automation and Skill Interpretation. International Journal of Creative and Open Research in Engineering and Management, <i>02</i>(04). https://doi.org/10.55041/ijcope.v2i4.795

Anandakumar, S., et al.. "InterviewBo: Multimodal Intelligence System for End-to-End Recruitment Process Automation and Skill Interpretation." International Journal of Creative and Open Research in Engineering and Management, vol. 02, no. 04, 2026, pp. . doi:https://doi.org/10.55041/ijcope.v2i4.795.

Anandakumar, S.,M. Mylesh,G. Elavarasan,S. Surya, and V. Gomathi. "InterviewBo: Multimodal Intelligence System for End-to-End Recruitment Process Automation and Skill Interpretation." International Journal of Creative and Open Research in Engineering and Management 02, no. 04 (2026). https://doi.org/https://doi.org/10.55041/ijcope.v2i4.795.

Search & Index

References

Mongkoljaturong, S. Chaiyasoonthorn & P. Prasertsakul (2025) – AI-powered MetaHuman interviewer: Serious game for student job interview skills.

Nagasawa, T. Minato, H. Ishiguro & K. Yamazaki (2024) – Adaptive interview strategy based on interviewees’ speaking willingness recognition for interview robots.– Explores adaptive interview techniques using behavioral analysis.

Zheng, Y. Liu & J. Zhang (2024) – Impact of artificial intelligence on recruitment biases.
– Studies how AI influences fairness and bias in hiring processes.

Kim, J. Lee & S. Lee (2023) – Fairness-aware multimodal learning in automatic video interview assessment. – Introduces fairness-aware models in AI-based interview evaluation.

Pota, A. Esposito, M. De Pietro & G. De Pietro (2022) – Decision model for HR allocation with self-assessment of skills.
– Proposes intelligent models for evaluating human resource capabilities.

-C. Hung & E.-P. Lim (2021) – Aggregating salaries from job post and review data.
– Analyzes job-related data for better recruitment insights.

Jayaratne & B. Jayatilleke (2020) – Predicting personality using open-ended interview answers.
– Uses NLP techniques for personality prediction from responses.

Obaid, S. Butt & M. Khan (2020) – Gamification for recruitment and job training. – Discusses gamified approaches for improving hiring processes.

Metahuman SDK (2024) – AI-based virtual human interaction platform.
– Provides tools for building realistic AI interview avatars.

Khallelullah et al. (2024) – Analysis of advanced technology integrated interviews.– Examines modern AI-driven interview systems and technologies.

Jadhav et al. (2024) – Mock interview simulator with AI and pose-based interaction. – Presents AI-based simulation systems for interview training.

Qin et al. (2024) – Automatic skill-oriented question generation for intelligent interviews.
– Focuses on AI-based question generation techniques.

-K. Lee et al. (2024) – Virtual reality and generative AI chatbot for interview simulations.
– Combines VR and AI chatbots for immersive interview practice.

K. Mishra et al. (2024) – AI-driven virtual mock interview development.– Develops AI-based platforms for interview preparation.

Li et al. (2023) – Ezinterviewer: Mock interview generator for improving performance.
– Introduces automated interview generation systems.

Ethical Compliance & Review Process

•All submissions are screened under plagiarism detection.
•Review follows editorial policy.
•Authors retain copyright.
•Peer Review Type: Double-Blind Peer Review
•Published on: Apr 28 2026

CCBYNC

This article is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. You are free to share and adapt this work for non-commercial purposes with proper attribution.

View License

Back to Volume 02, Issue 04 View All Issues Next Article

← Previous Article

Intelligent Systems for Cyberbullying Detection and Response

Next Article →

InterviewEase: A Smart AI Interviewing System for Role-Specific Technical, Behavioral, and Coding Assessment