EmoConfident Interviewer :An AI Mock Interview Evaluator

2015 11th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition (FG), 2015

Ever wondered why you have been rejected from a job despite being a qualified candidate? What went wrong? In this paper, we provide a computational framework to quantify human behavior in the context of job interviews. We build a model by analyzing 138 recorded interview videos (total duration of 10.5 hours) of 69 internship-seeking students from Massachusetts Institute of Technology (MIT) as they spoke with professional career counselors. Our automated analysis includes facial expressions (e.g., smiles, head gestures), language (e.g., word counts, topic modeling), and prosodic information (e.g., pitch, intonation, pauses) of the interviewees. We derive the ground truth labels by averaging over the ratings of 9 independent judges. Our framework automatically predicts the ratings for interview traits such as excitement, friendliness, and engagement with correlation coefficients of 0.73 or higher, and quantifies the relative importance of prosody, language, and facial expressions. According to our framework, it is recommended to speak more fluently, use less filler words, speak as "we" (vs. "I"), use more unique words, and smile more.

IAEME PUBLICATION , 2021

Recently applicant information services and interview-assistance services based on big data and AI technology are distributed rapidly worldwide to introduce an interview system that secures efficiency and fairness in the job interview market. Accordingly, this study presents an AI-based interview system developed based on deep-learning technology in which more than 100,000 evaluation data sets were derived from 400,000 interview image data sets. The resulting AI interview system has been applied to enterprises with a reliability of 0.88 Pearson score. Particularly, applying this system to 5 major public enterprises in Korea is presented in this paper. It turned out that the level of satisfaction with fairness and efficiency was as high as 85% in such aspects as evaluation processes, job fitness, and organization fitness. As the applicable range of AI-based solutions is expanding to the general area of personnel management with its time and cost efficiency, as well as reliability and fairness recognized, the deep learning-based job interview solution proposed by the present study needs to be applied widely to written examinations and personality and aptitude tests.

International journal of engineering research and technology, 2021

With artificial intelligence (AI) system we can predict human skill and its recommended job type as currently industry with employment agency needs to have AI introduced in it. With the help of all machine learning algorithms such as Naïve bayes, random forest, SVM, of convolutional neural network (CNN). Emotion of an employee, employees voice converted to text, face based company verification process will be done in this project. In the future system user can access user record ana analyzed the efficiency and how effective it is. Students also can get benefit by analyzing themselves with emotion and personality with this system as in the future we might see such system in the interview process. In the future system user can access user record ana analyzed the efficiency and how effective it is. Students also can get benefit by analyzing themselves with emotion and personality with this system as in the future we might see such system in the interview process.

International Journal of All Research Education and Scientific Methods (IJARESM), 2024

AI has impacted STEM education and expanded employment by implementing new approaches to standard problems. Pre-interview assessment sites employing artificial intelligence enable candidates to prepare for STEM job interviews while saving cost and time. These platforms incorporate tools, including NLP and machine learning algorithms, to estimate technical and behavioral performance constructively and objectively in real-time. In contrast to conventional mock interviews that are generally subjective, available in limited numbers, and expensive to administer, AI platforms result in more effective interview simulations based on the candidate's skills and the requirements for the specific job. These call for coding excellence, system design questions, and soft skills whereby applicants are tested and allowed to demonstrate problem-solving, communication, and leadership. Utilizing interview questions and answers based on a candidate's performance provides flexibility that the market has yet to embrace fully. The extensibility and availability of the platforms also do well in fulfilling the shortage of mock interviews for candidates, especially where they are in regions or have limited access to such services. However, some key challenges still exist, including bias in the AI systems and data privacy issues. Adjusting the machine learning model's data sets, including interview data and user feedback, is crucial for enhancing precision and pertinence. When applied and adopted, AI can enhance the production of interview preparation content for STEM graduates across the globe, thereby equalizing chances for talented and deserving candidates while reinventing the recruitment process.

IRJET, 2021

Post Covid times have made it difficult to meet personally and get to know the potential candidates on individual basis. Although, advances in AI has made it possible to successfully recognize personality traits and other nonverbal cues with the help of camera. In this study, Convolutional neural network (CNN) using Deep learning (DL) has been taken in use to extract personality traits from video and speech feeds to output desired results.

2017 Seventh International Conference on Affective Computing and Intelligent Interaction (ACII)

Online video-based job interviews are becoming very popular in the screening of potential employees. In this study, we collected a corpus of 1891 monologue job interview videos (63 hours in duration) from 260 online workers. These videos were annotated for personality traits and hiring recommendation score by experts from a major assessment company. We proposed a unified method of automatic analysis that consists of using clustering to convert continuous audio/video analysis output to discrete pseudoword documents, and then applying modern text classification methods to process speech content, prosody and facial expressions. Our experiments showed that using what the interviewees say (i.e., spoken text), we can predict their personality traits such as openness, conscientiousness, extraversion, agreeableness, and emotional stability with an Fmeasure of 0.8 or better, while we get an F-measure of 0.6 in predicting hiring recommendation score. Prosody and facial expressions added limited usefulness on interview judgments and need further investigation.

Proceedings of the 28th International Conference on Intelligent User Interfaces

The most popular way to assess talent around the world is through interviews. Interviewers contribute substantially to candidate experience in many organizations' hiring strategies. There is a lack of comprehensive understanding of what makes for a good interview experience and how interviewers can conduct candidate-centric interviews. An exploratory study with 123 candidates revealed critical metrics about interviewer behavior that affects candidate experience. These metrics informed the design of our AI-driven SmartView system that provides automated post-interview feedback to Interviewers. Real-world deployment of the system was conducted for three weeks with 35 interviewers. According to our study, most interviewers found that SmartView insights helped identify areas for improvement and could assist them in improving their interviewing skills.

IAEME PUBLICATION, 2020

Recruitment and selection of human talent is an important process for a company or organization because hiring new people directly influences the institution's process. One of the most important and recognized activities of this process is the job interview, despite this, there are few investigations that help the candidate to have an adequate preparation to face this process and little data to carry out a system capable of helping to improve the process. Being able to know the preferences of the user or the ideas they have about an interviewer, would facilitate the improvement of the current process in the interviews and would be very important for carrying out implementations in order to improve the processes. For this reason, in the present study, an analysis of the person's reactions to an interviewer character is carried out through a mobile system, and their preferences are known through a survey to complement the desired information. The results obtained from the analysis are intended to help this research area and to facilitate the creation of a system that is considered as future work.

Journal of emerging technologies and innovative research, 2019

This paper presents a review on various techniques on predicting the interview performance autonomously using machine learning techniques and analyze the audio-visual features using an interface-based video interview by a virtual agent. Different scenarios are studied and compared for a better understanding of human behavior in case of the video interview. In this paper, the existing optimization techniques are reviewed according to their methodologies and advantages. Based on the review, research gaps are observed and the references are provided for further research work. Index Terms Interface based video interviews, Automatic job prediction, Machine learning for job prediction, Nonverbal behavior prediction, Regression, Deep learning for audio-visual predictions.

Lecture Notes in Computer Science, 2013

This demo presents an approach to recognising and interpreting social cues-based interactions in computer-enhanced job interview simulations. We show what social cues and complex mental states of the user are relevant in this interaction context, how they can be interpreted using static Bayesian Networks, and how they can be recognised automatically using state-of-the-art sensor technology in real-time.