ForDigitStress: A multi-modal stress dataset employing a digital job interview scenario

TL;DR

This paper introduces ForDigitStress, a multi-modal dataset collected during digital job interviews, including audio, video, and physiological data, with stress annotations, and evaluates machine learning classifiers for stress detection.

Contribution

The paper provides a novel multi-modal stress dataset from digital interviews with comprehensive annotations and baseline machine learning performance metrics.

Findings

Best classifier achieved 88.3% accuracy

F1-score of 87.5% for stress classification

Multi-modal data enhances stress detection capabilities

Abstract

We present a multi-modal stress dataset that uses digital job interviews to induce stress. The dataset provides multi-modal data of 40 participants including audio, video (motion capturing, facial recognition, eye tracking) as well as physiological information (photoplethysmography, electrodermal activity). In addition to that, the dataset contains time-continuous annotations for stress and occurred emotions (e.g. shame, anger, anxiety, surprise). In order to establish a baseline, five different machine learning classifiers (Support Vector Machine, K-Nearest Neighbors, Random Forest, Long-Short-Term Memory Network) have been trained and evaluated on the proposed dataset for a binary stress classification task. The best-performing classifier achieved an accuracy of 88.3% and an F1-score of 87.5%.