Interview Preparation System Using AI

Year : 2025 | Volume : 12 | Issue : 01 | Page : 8 13
    By

    Shruti Patil,

  • Smita Badarkhe,

  • Neha Patil,

  • Rutuj Nagargoje,

  1. Student, Department of Electronics & Telecommunication, Smt. Kashibai Navale College of Engineering, Savitribai Phule Pune University, Pune, Maharashtra, India
  2. Assistant Professor, Department of Electronics & Telecommunication, Smt. Kashibai Navale College of Engineering, Savitribai Phule Pune University, Pune, Maharashtra, India
  3. Student, Department of Electronics & Telecommunication, Smt. Kashibai Navale College of Engineering, Savitribai Phule Pune University, Pune, Maharashtra, India
  4. Student, Department of Electronics & Telecommunication, Smt. Kashibai Navale College of Engineering, Savitribai Phule Pune University, Pune, Maharashtra, India

Abstract

The automated interview evaluation system leverages artificial intelligence (AI) and natural language processing (NLP) technologies to streamline and enhance the interview process. Through a web-based application built with the Flask framework, the system enables candidates to respond to dynamically loaded interview questions using both text and speech inputs. Questions, managed via a CSV (comma separated values) file for flexibility, are evaluated for similarity to expected answers using the rapid fuzz library, providing an objective assessment metric. The system employs Google’s speech recognition API (application programming interface) to process spoken responses, ensuring accessibility and ease of use. Results, including average similarity scores, are presented to both candidates and interviewers, offering clear and actionable feedback. By integrating AI, NLP, and advanced web technologies, the system aims to provide a robust and user-friendly platform for consistent and fair interview evaluations, enhancing the overall efficiency and effectiveness of the interview process. This project presents an innovative interview system designed to enhance the efficiency and accuracy of evaluating candidates’ responses in interview settings. Developed using the Flask web framework, this system leverages both textual and speech input to provide a versatile and accessible interview experience. The application consists of three primary components: the user interface, the backend processing, and the evaluation mechanism. The user interface, implemented with HTML and CSS (cascading style sheet), provides a seamless and intuitive platform for candidates to interact with. It includes pages for initiating the interview, answering questions, and viewing results. The backend, developed in Python with Flask, handles routing, data management, and speech recognition integration using the `speech recognition` library. Interview questions are dynamically loaded from a CSV file, ensuring flexibility and ease of updating content. Candidates can respond to interview questions either by typing their answers or by using speech input, which is processed using Google’s speech recognition API. The system records these responses and evaluates them against expected answers using the “rapid fuzz” library, which calculates the similarity score between the provided and expected answers. This scoring mechanism provides an objective measure of the candidate’s performance. The results page displays the final assessment, including the average similarity score, offering both the candidate and the interviewer a clear understanding of the interview outcomes. This system enhances the interview process by making it more efficient while ensuring all candidates are evaluated consistently and fairly. Overall, this project demonstrates the effective integration of web technologies and NLP tools to create a robust and user-friendly interview system. It stands as a testament to the potential of combining traditional web development with advanced speech and text processing capabilities to improve conventional processes.

Keywords: Natural language processing (NLP), structured query language (SQL), artificial intelligence (AI), speech processing, interview

[This article belongs to Journal of Multimedia Technology & Recent Advancements ]

How to cite this article:
Shruti Patil, Smita Badarkhe, Neha Patil, Rutuj Nagargoje. Interview Preparation System Using AI. Journal of Multimedia Technology & Recent Advancements. 2025; 12(01):8-13.
How to cite this URL:
Shruti Patil, Smita Badarkhe, Neha Patil, Rutuj Nagargoje. Interview Preparation System Using AI. Journal of Multimedia Technology & Recent Advancements. 2025; 12(01):8-13. Available from: https://journals.stmjournals.com/jomtra/article=2025/view=203055


References

  1. Mandal R, Lohar P, Patil D, Patil A, Wagh S. AI-based mock interview evaluator: an emotion and confidence classifier model. In: 2023 International Conference on Intelligent Systems for Communication, IoT and Security (ICISCoIS), Coimbatore, India, February 9–11, 2023. pp. 521–526.
  2. Tadvalkar A, Ingale M, Chaudhari S, Chaudhari M. Automated HR interview system. Int Res J Eng Technol. 2021; 8 (5): 3645–3648.
  3. Bagaria V, Badve M, Beldar M, Ghane S. An intelligent system for evaluation of descriptive answers. In: 2020 3rd International Conference on Intelligent Sustainable Systems (ICISS), Thoothukudi, India, December 3–5, 2020. pp. 19–24.
  4. Su MH, Huang KY, Yang TH, Lai KJ, Wu CH. Dialog state tracking and action selection using deep learning mechanism for interview coaching. In: 2016 International Conference on Asian Language Processing (IALP), Tainan, Taiwan, November 21–23, 2016. pp. 6–9.
  5. Purohit J, Bagwe A, Mehta R, Mangaonkar O, George E. Natural language processing based Jaro – the interviewing chatbot. In: 2019 3rd International Conference on Computing Methodologies and Communication (ICCMC), Erode, India, March 27–29, 2019. pp. 134–136.
  6. Kumar K, Kumar A, Abhishek K, Singh DK. Automation of HR interview system using JESS inference engine. In: 2014 Fourth International Conference on Communication Systems and Network Technologies, Bhopal, India, April 7–9, 2014. pp. 1102–1105.
  7. Suen HY, Hung KE, Lin CL. TensorFlow-based automatic personality recognition used in asynchronous video interviews. IEEE Access. 2019; 7: 61018–61023.
  8. Yang M, Tao Y, Cai H, Hu B. Behavioral information feedback with large language models for mental disorders: perspectives and insights. IEEE Trans Comput Soc Syst. 2024; 11 (3): 3026–3044.
  9. Patil P, Patil S, Miniyar V, Bandal A. Subjective answer evaluation using machine learning. Int J Pure Appl Math. 2018; 118 (24): 1–3.
  10. Ramamurthy M, Krishnamurthi I. Design and development of a framework for an automatic answer evaluation system based on similarity measures. J Intell Syst. 2017; 26 (2): 243–262.
Regular Issue Subscription Review Article
Volume 12
Issue 01
Received 03/07/2024
Accepted 13/01/2025
Published 07/03/2025
Publication Time 247 Days
186

Login


My IP

PlumX Metrics