2020/06/14 by Anumeha Agrawal, Rosa Anil George, Agrawal, Anumeha +7
Psychology · #Computation and Language (cs.CL) #Computer Vision and Pattern Recognition (cs.CV) #Emotion and Mood Recognition #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML)
paper · pdf · doi:10.48550/arxiv.2006.07909
openalex publication_date 2020/06/14 · openalex created_date 2022/07/26 · openalex updated_date 2026/07/28
Behavioral cues play a significant part in human communication and cognitive\nperception. In most professional domains, employee recruitment policies are\nframed such that both professional skills and personality traits are adequately\nassessed. Hiring interviews are structured to evaluate expansively a potential\nemployee's suitability for the position - their professional qualifications,\ninterpersonal skills, ability to perform in critical and stressful situations,\nin the presence of time and resource constraints, etc. Therefore, candidates\nneed to be aware of their positive and negative attributes and be mindful of\nbehavioral cues that might have adverse effects on their success. We propose a\nmultimodal analytical framework that analyzes the candidate in an interview\nscenario and provides feedback for predefined labels such as engagement,\nspeaking rate, eye contact, etc. We perform a comprehensive analysis that\nincludes the interviewee's facial expressions, speech, and prosodic\ninformation, using the video, audio, and text transcripts obtained from the\nrecorded interview. We use these multimodal data sources to construct a\ncomposite representation, which is used for training machine learning\nclassifiers to predict the class labels. Such analysis is then used to provide\nconstructive feedback to the interviewee for their behavioral cues and body\nlanguage. Experimental validation showed that the proposed methodology achieved\npromising results.\n