A fuzzy supply chain risk assessment approach using real-time disruption event data from Twitter
Enterprise Information Systems
Taylor & Francis
School of Science
In this study, we develop a novel methodology to identify supply chain disruption events using Twitter feeds in real time. Underpinned by advances in Natural Language Processing (NLP) and machine learning, we propose an approach that includes a state-of-the-art variant of Conditional Random Field (CRF) model for event annotation, location-based clustering of the annotated events, and a fuzzy inference system to evaluate supply chain risk. We validate the new approach through a text corpus derived from a Twitter data stream, which is a popular method in NLP. The results show that the proposed model outperforms the baseline model.