Leveraging natural language processing and community detection for shaping manufacturing communities in social manufacturing

Social manufacturing (SocialMfg), as an emerging paradigm, leverages socialized manufacturing resource nodes (SMRNs) grouped into manufacturing communities (MCs) through cyber-physical-social connections to collectively create, produce, and share goods and services. Despite its nascent stage, the potential impact of SocialMfg on mass personalization and sustainability is significant, prompting manufacturing enterprises to increasingly adopt this model facilitated by various industrial Internet platforms (IIPs). However, SMRNs face challenges such as trust and reputation and alignment of interests when forming MCs. This article proposes an approach that integrates natural language processing and community detection algorithm to autonomously form relevant MCs among SMRNs on IIPs. A novel BERT-like model, SoManBERT, is introduced to accurately classify the manufacturing interests and roles of SMRNs, revealing their expertise. Subsequently, a recommender system, integrating trust scores and a modified-density-peaks-based overlapping community detection (DPOCD) algorithm, is designed to recommend reliable SMRNs with similar manufacturing interests or roles to each other. The effectiveness of the proposed approach is verified through a case study on a SocialMfg prototype system. Empirical evaluations reveal that this approach surpasses baseline methods, demonstrating its potential for SocialMfg environments.