Job Interview Training System using Multimodal Behavior Analysis

Takeuchi, Naonobu; Koda, T.

doi:10.1109/aciiw52867.2021.9666270

Cited by 2 publications

(2 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Naim et al [16] use both verbal and non-verbal features to assess soft skills such as friendliness, engagement, and hiring recommendations. In addition, a system that recognizes the non-verbal behaviors of candidates was proposed [2] and platforms that evaluate candidates using various features were suggested [3], [4].…”

Section: Background and Related Work A Automated Assessment Of Job In...mentioning

confidence: 99%

“…Although AVIs can provide opportunities to a larger pool of applicants, the task of evaluating a substantial number of recorded videos with a limited number of interviewers can be inefficient and time-consuming. To address the inherent challenges associated with interview assessments relying solely on human, automated video interview assessment systems that combine powerful machine learning algorithms have recently emerged [2]- [5]. An automated video interview assessment system gathers human-labeled interview scores by reviewing pre-recorded interview videos of the applicants.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Fairness-Aware Multimodal Learning in Automatic Video Interview Assessment

Kim,

Choi,

Yoon

et al. 2023

IEEE Access

View full text Add to dashboard Cite

With the ever-growing reliance on Artificial Intelligence (AI) across diverse domains, there is an increasing concern surrounding the possibility of biases and unfairness inherent in AI systems. Fairness problems in automatic interview assessment systems, especially video-based automated interview assessments, have less been addressed despite their prevalence in the recruiting field. In this paper, we propose a method that resolves fairness problems in an automated interview assessment system that uses multimodal data as input. This is mainly done by minimizing the Wasserstein distance between two sensitive groups by introducing a regularization term. Subsequently, we employ a hyperparameter that can control the trade-off between fairness and accuracy. To test our method in various data settings, we suggest a preprocessing method that can manually adjust the underlying degree of unfairness in the training data. Experimental results show that our method presents state-of-the-art results in terms of fairness compared to previous methods.

show abstract