Αn AI-driven approach to assess sentiments and interpret context in a critical mineral supply chain
Bibliographic record
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.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.004 | 0.016 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.003 | 0.002 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.004 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".