ISSN (Online) 2581-9429

IJARSCT
International Journal of Advanced Research in Science, Communication and Technology (IJARSCT)
International Open-Access, Double-Blind, Peer-Reviewed, Refereed, Multidisciplinary Online Journal
Impact Factor: 7.301 Volume 3, Issue 1, November 2023

AI Based Mock Interview Evaluator and Analysis:

to Analyze Emotion, Confidence, and Knowledge
Prof. H. R. Agashe, Dhanashri Anwat, Prajakta Derle, Payal Nagare, Siddhi Dhavale
Department of Information Technology
Matoshri College of Engineering and Research Center, Eklahare, Nashik, Maharashtra, India
[email protected], [email protected], [email protected], [email protected]

Abstract: Mock interviews are an excellent way to practice for a real job interview. When you conduct a
practice interview, you put yourself in a situation that is similar to an actual job interview. It allows job
seekers to practice, receive feedback, and improve their skills. A mock interview can also help you develop
interview strategies, improve your communication skills, answer difficult questions, and alleviate the nerves
that many people feel before a real job interview.
Mock interviews offer a safe environment in which to practice and develop important interview skills such
as effective communication, problem-solving, and interpersonal skills. Mock interviews help people gain
confidence and reduce anxiety, allowing them to be more comfortable and composed during actual
interviews.
Mock interviews provide constructive feedback, allowing individuals to identify and work on areas of
weakness. Mock interviews expose candidates to different interview formats and styles, ensuring that they
are better prepared for various types of interviews, such as behavioral, technical, and panel
Individuals can improve their self-presentation skills, such as body language, attire, and overall demeanor,
by participating in mock interviews.
Practicing with a variety of interview questions in mock interviews allows people to develop well-
structured and compelling responses.Mock interviews teach candidates how to effectively manage their time
during an interview, ensuring they address key points within the time allotted. Mock interviews help people
clarify their career goals and objectives, which can result in more focused and successful interviews.Those
who spend time practicing mock interviews outperform their peers in real interviews, giving them a
competitive advantage in the job market interviews.

Keywords: Financial Time Series, Accuracy, Investment Strategies, Market indicators.

I. INTRODUCTION
Mastering the art of interviews is a critical skill for career success in today's competitive job market.The "AI-Based Mock
Interview Evaluator" is a cutting-edge software solution that is set to change the way people prepare for job interviews.
This project uses artificial intelligence (AI) to create a comprehensive and dynamic platform for interview practice and
improvement.
The AI-Based Mock Interview Evaluator addresses the difficulties that job seekers and students encounter when
attempting to improve their interview skills. This application provides a realistic and instructive simulated interview
experience using advanced AI technologies. It not only facilitates practice but also provides invaluable feedback,
making it a must-have tool for professional success.
The "Mock Interview Evaluator" is intended to help job candidates and students improve their interview skills. The
primary goal of this project is to develop an automated system that simulates interview scenarios and provides feedback
based on the performance of the user.
The "Mock Interview Evaluator" project seeks to bridge the gap between theory and practice by providing users with
valuable insights and constructive feedback in order to improve their interviewskills and increase their chances of success
in the job market.

Copyright to IJARSCT DOI: 10.48175/568 273

www.ijarsct.co.in
 ISSN (Online) 2581-9429
IJARSCT
International Journal of Advanced Research in Science, Communication and Technology (IJARSCT)
International Open-Access, Double-Blind, Peer-Reviewed, Refereed, Multidisciplinary Online Journal
Impact Factor: 7.301 Volume 3, Issue 1, November 2023

II. MOTIVATION
The goal is to create a system that is both efficient and productive. The main goal of the system is to analyze the mock
interview based on various parameters and provide analysis to the user for improvement.

III. PROBLEM STATEMENT

"How can we effectively assess and provide valuable feedback to job seekers participating in mock interviews to help
them improve their interview skills, boost their confidence, and increase their chances of securing their desired job
positions?"This problem statement summarizes the main challenges that mock interview evaluators face, such as the
need for structured assessment criteria, the ability to provide constructive feedback, and the overall goal of assisting
candidates in their career pursuits.

IV. PROPOSED SYSTEM

For our interactive scenario, we rely on a software framework that allows for fine-grained multimodal behavior control
for virtual characters. In this environment, the virtual character plays the role of a recruiter who reacts and adapts to the
user's behavior using an automatic recognition of social cues component. A knowledge elicitation study with real job
seekers was used to identify the social cues relevant to job interviews. Finally, two user studies are presented to
investigate the feasibility of the proposed approach as well as the impact of such a system on users.

 Facial Expression Analysis

 Grammar Analysis
 Display Questions
 Display Result

V. ALGORITHMS
5.1 Convolutional Neural Network CNN)
A CNN (Convolutional Neural Network) algorithm is typically used in a mock interview evaluator to assess a
candidate's performance. The evaluator records the mock interview sessions on audio and video, including the
candidate's responses and body language. The audio and video data are preprocessed in order to extract useful features.
In the case of audio, this could include speech recognition, which converts spoken words into text. Face detection and
tracking in video could be used to analyze the candidate's facial expressions and gestures.
Based on the learned patterns, it evaluates various aspects of the interview, such as clarity of speech, confidence, eye
contact, and more. Based on its analysis, the CNN generates feedback that provides insights into the candidate's
performance.

5.2 NLP
Natural Language Processing (NLP) is critical in AI-powered Mock Interview Evaluators. The candidate's spoken
words are converted into text using NLP. This is necessary for analyzing the interview responses' content. Automatic
speech recognition (ASR) systems are frequently used to accurately transcribe spoken words. The transcribed text,
which includes the candidate's responses to interview questions, is analyzed using NLP. The candidate's answers are
evaluated using NLP techniques for clarity, relevance, and coherence. The sentiment of the candidate's responses can be
determined using NLP. This aids in determining whether the candidate's emotional tone during the interview is
enthusiastic, confident, or nervous.
NLP models can understand the semantic meaning of the candidate's responses, allowing them to assess the candidate's
depth of knowledge and ability to provide insightful and relevant information.

5.3 Web Scrapping

Web scraping can be used to collect interview questions, answers, and other relevant data from a variety of online
sources, such as job boards, forums, or company websites. This information can be used to create a diverse and
comprehensive database of interview content. The scraped data can be used by AI models to generate interview
Copyright to IJARSCT DOI: 10.48175/568 274
www.ijarsct.co.in
 ISSN (Online) 2581-9429
IJARSCT
International Journal of Advanced Research in Science, Communication and Technology (IJARSCT)
International Open-Access, Double-Blind, Peer-Reviewed, Refereed, Multidisciplinary Online Journal
Impact Factor: 7.301 Volume 3, Issue 1, November 2023

questions covering a wide range of topics and difficulty levels. These questions can be customized for specific job
functions or industries. In addition to scraping questions, the AI system can collect model answers or expected
responses from a variety of sources. This can be used to develop an answer key for assessing candidate responses.
Web scraping can keep the question database and answer keys up to date. As new job-market questions and trends
emerge, the system can automatically update its content. Web scraping is an important part of gathering and curating
the data required to create and maintain an AI-based mock interview evaluator. It allows the system to remain relevant,
diverse, and adaptable in the face of changing job market dynamics.

5.4 Pydub Audio Python Libraries

The Python PyDub library is useful for audio processing tasks such as audio file format conversion,slicing, merging, and
more. PyDub can be used in an AI-based Mock Interview Evaluator to handle audio aspects of the evaluation
process.Record and save audio files of the candidate's responses during the mock interview using PyDub.Convert the
recorded audio files to a standard format (suchas WAV or MP3) that can be analyzed and stored. PyDub can be used to
split the audio files into segments if you want to break down the interview into segments (e.g., question, response,
feedback).You can integrate PyDub with speech-to-text libraries like SpeechRecognition to transcribe the candidate's
responses into text for analysis. PyDub can be used for basic audio analysis, such as extracting features such as
pitch, tone, or pauses in a candidate's speech, which can be useful in assessing speaking abilities.

VI. METHODOLOGY

VII. CONCLUSION
Finally, mock interview evaluators and analysis play an important role in job seekers' quest for employment. They help
candidates become more effective interviewees by bridging the gap between preparation and execution mode. This role
not only benefits job seekers, but it also provides personal fulfillment and skill development for the evaluators.

REFERENCES
[1] Ming-Hsiang Su, Kun-Yi Huang, Tsung-Hsien Yang, Kuan-Jung Lai and Chung-Hsien Wu " Dialog State
Tracking And Action Selection Using Deep Learning Mechanism For Interview Coaching".
[2] "Michael K. Brown and Jay G. Wilpon"A Grammar Compiler for Connected Recognition.
[3] Hung-Yue Suen1, Kuo-En Hung1, and Chien-Liang Lin "Tensor Flow-based Automatic Personality
Recognition Used in Asynchronous Video Interviews"
[4] Hongli Zhang, Alireza Jolfaei, And Mamoun Alazab "A Face Emotion Recognition Method Using
Convolutional Neural Network and Image Edge Computing".

Copyright to IJARSCT DOI: 10.48175/568 275

www.ijarsct.co.in
 ISSN (Online) 2581-9429
IJARSCT
International Journal of Advanced Research in Science, Communication and Technology (IJARSCT)
International Open-Access, Double-Blind, Peer-Reviewed, Refereed, Multidisciplinary Online Journal
Impact Factor: 7.301 Volume 3, Issue 1, November 2023

[5] Tengfe Song, Wenming Zheng, Cheng Lu, Yuanzong, Xilei Zhang1and Zhen Cui "MPED: A Multi-Modal
Physiological Emotion Database for Discrete Emotion Recognition" IEEE Access, vol. 7, pp. 12177–12191,
2019.
[6] Erdenebileg Batbaatar, Meijing Li, And Keun Ho Ryu "Semantic-Emotion Neural Network for Emotion
Recognition from Text" IEEE Access, vol. 7, pp. 111866–111878,2019.
[7] Michael K. Brown and Jay G. Wilpon “A Grammar Compiler for Connected Recognition Speech” IEEE
TRANSACTIONS ON SIGNAL PROCESSING, VOL. 39. NO. 1, JANUARY 1991
[8] R. MacDonald, “Disconnected youth? social exclusion, the underclass and economic marginality,”Social
Work and Society, vol. 6, no. 2, pp.236–247, 2008.

Copyright to IJARSCT DOI: 10.48175/568 276

www.ijarsct.co.in