Article Sidebar
Published:
Sep 8, 2025Keywords:
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
ACE journal provides immediate open access to all content on the principle that making research freely available to the public supports a greater global exchange of knowledge. ACE grants usage rights to others using the open license CC-BY-NC allowing for immediate free access to the work and permitting any user to read, download, copy, distribute, print, search, or link to the full texts of articles, crawl them for indexing, pass them as data to software, or use them for any other lawful purpose.
Main Article Content
An AI-based framework for improving efficiency and fairness in the interview process
Abstract
Artificial intelligence (AI) technologies have advanced to the point where they can assist human resource specialists, such as recruiters, by automating major aspects of the hiring process and efficiently filtering candidate pools. However, limited research has evaluated the effectiveness of AI systems in virtual interviews. This paper presents InstaJob, an AI-powered framework designed to enhance both
efficiency and fairness in the hiring pipeline. The system integrates multiple deeplearning components to analyze candidate responses during interviews. Facial emotion recognition is performed using a convolutional neural network (CNN) trained on the FER2013 dataset, achieving a validation accuracy of 77% and outperforming several state-of-the-art approaches. For speech processing, IBM Watson is used to convert spoken responses into text. The transcribed text is then analyzed using EmoRoBERTa, a transformer-based model, to detect emotional signals from verbal content. In addition, IBM Watson is employed to detect filler words and assess speech fluency. These components collectively enable InstaJob to assess candidates’ soft skills in a structured and unbiased manner, offering a comprehensive and datadriven evaluation of interview performance.
