<p>Human–Computer Interaction has been evolved rapidly into talent acquisition using most frequently adopted technology in recent times in various domain of application. With introduction to modernized technological adoption, both the scope and limitation of deploying Human–Computer Interaction towards hiring process has been witnessed. In this perspective, Artificial Intelligence (AI) can play a significant role towards bridging the gap by increasing scope and minimizing limitation. Review of existing literatures is witnessed with various AI-models towards facilitating decision making for talent acquisition. However, majority of existing approaches are found to offer less-optimal applicability when it comes to real-world recruitment process bearing inherent issues of model biasness. Hence, the proposed system addresses this issue by introducing a novel and innovative computational framework of human–computer interaction powered by AI considering multi-modality-based method. According to this scheme, the latent sentiment of an applicant is extracted from video feeds, facial expression, and speech concurrently during the interview process where an explicit usage of Convolution Neural Network (CNN), descriptive statistical approach, supervised machine learning approach using Artificial Neural Network (ANN) and Support Vector Machine (SVM) is carried out respectively. The benchmarked outcome is found with cumulative predictive outcome for extracting latent sentiment with 11% of increased accuracy, 39% of reduced validation time, 27% of reduced latency, 26% of reduced cost, and 37% of minimized processing time.</p>