Αn AI-driven approach to assess sentiments and interpret context in a critical mineral supply chain

Abstract

This exploratory article argues against using Large Language Models (LLMs) as a ‘black box’, without human scrutiny, for generating interpretable context while assessing sentiment metrics. These metrics support supply chain (SC) decision-making under information asymmetry and public policies in critical mineral networks. Using a dataset of 5,168 news articles before and after a truck strike in the Democratic Republic of Congo (DRC), we enumerate observed sentiment shifts across cobalt SC echelons (i.e., DRC, China, U.S.A. and Canada) using an LLM with long context windows. As shifts can be small, assessments need to be precise, significant, and interpretable. To this end, we devise and deploy a ‘Context Enhanced Supply Chain Sentiment and Summaries’ (CESCSS) framework to provide reliable and interpretable outcomes. Through statistical testing, our findings indicate that context matters in assessing sentiment shifts across SC operations echelons. Findings also illustrate differences in sentiments and offer context summary-based interpretations for these differences based on end-to-end information asymmetries. In addition, results showcase the reliability of human ratings and then demonstrate that human assessments are statistically equivalent to context-enhanced LLM sentiment valuations. We discuss pathways for applying the CESCSS framework toward theory development and managerial decisions in critical mineral SCs.