Human-centricity in Industry 5.0-revealing of hidden research topics by unsupervised topic modeling using Latent Dirichlet Allocation

Purpose - The set of 2,509 documents related to the human -centric aspect of manufacturing were retrieved from Scopus database and systmatically analyzed. Using an unsupervised machine learning approach based on Latent Dirichlet Allocation we were able to identify latent topics related to human -centric aspect of Industry 5.0. Design/methodology/approach- This study aims to create a scientific map of the human -centric aspect of manufacturing and thus provide a systematic framework for further research development of Industry 5.0. Findings - In this study a 140 unique research topics were identified, 19 of which had sufficient research impact and research interest so that we could mark them as the most significant. In addition to the most significant topics, this study contains a detailed analysis of their development and points out their connections. Originality/value- Industry 5.0 has three pillars - human -centric, sustainable, and resilient. The sustainable and resilient aspect of manufacturing has been the subject of many studies in the past. The human -centric aspect of such a systematic description and deep analysis of latent topics is currently just passing through.