Stress and Machine Learning: Future with Possibilities- A Bibliometric Approach

Objectives: Stress in human life is a global health concern and machine learning based models have been applied extensively for the stress prediction. This work is an attempt to present a bibliometric analysis in the field of stress prediction using machine learning. Design/Methodology: The dataset to conduct this study was taken from the Web of Science database and research papers were selected from the year 2005 to 2021. Then, bibliometric analysis tool, VOS Viewer 1.6.14 was applied for generating a co-authorship network map, inter-country co-authorship network map, and keywords co-occurrences network maps. Findings: The outcomes of this study visually highlight the important research details like the most prolific journal, most cited paper, most prolific country, institution and interesting research driving points in the stress prediction using machine learning. Originality: This study attempts to portray the existing literature on stress prediction using machine learning more comprehensively and systematically by showing research collaboration among countries, authors, co-citations analysis and, bibliographic coupling. The findings of this study can be useful to conduct future research on a similar area.

Keywords: Bibliographic coupling, Bibliometric analysis, Machine learning, Stress prediction, VOSviewer.