A fuzzy supply chain risk assessment approach using real-time disruption event data from Twitter

Naeem Khalid Janjua, Falak Nawaz, Daniel D. Prior

Research output: Contribution to journalArticlepeer-review

16 Citations (Scopus)

Abstract

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.

Original languageEnglish
Article number1959652
Number of pages22
JournalEnterprise Information Systems
Volume17
Issue number4
Early online date2 Aug 2021
DOIs
Publication statusPublished - 2023
Externally publishedYes

Keywords

  • fuzzy logic
  • natural language processing
  • risk assessment
  • social media
  • Supply chain

Fingerprint

Dive into the research topics of 'A fuzzy supply chain risk assessment approach using real-time disruption event data from Twitter'. Together they form a unique fingerprint.

Cite this