focalinterest.com

AI Summary of Peer-Reviewed Research

This page presents an AI-generated summary of a published research paper. The original authors did not write or review this article. [See full disclosure ↓]

Publishing process signals: STANDARD — reflects the venue and review process. — venue and review process.

Geopolitical risk sentiment predicted some market changes

—

in
A man in a white dress shirt sits at a desk in a modern office, viewing multiple computer monitors displaying financial charts, market graphs, and data visualizations with his hand near his face in a contemplative pose.
Research area:Economics, Econometrics and FinanceEconomics and EconometricsGranger causality

What the study found

The study found that a time series built from multilingual X/Twitter sentiment about geopolitical risk contained predictive information for several financial assets and market changes at different lag times. The finding is based on the period around the start of the Ukraine War.

Why the authors say this matters

The authors suggest that tracking geopolitical risk sentiment across multiple languages may help capture worldwide reactions to major events such as the Ukraine War. They conclude that the sentiment time series has predictive information for some financial asset and market changes.

What the researchers tested

The researchers examined changes in financial assets and markets from December 1, 2021, to April 30, 2022. They collected more than 3.6 million tweets in seven languages, used Goldstein 1992 positive and negative geopolitical risk bigrams, applied sentiment analysis methods, and tested the relationship between the resulting daily sentiment time series and 39 financial assets and markets using Granger causality.

What worked and what didn't

The geopolitical risk sentiment time series showed predictive information for several assets and market changes at different lag times. The abstract does not specify which assets or markets were affected, which methods performed best, or which tests did not show a relationship.

What to keep in mind

The available summary does not describe limitations in detail. The results are limited to the study period around the early phase of the Ukraine War and to the 39 assets and markets examined.

Key points

  • More than 3.6 million tweets were collected in seven languages.
  • The study focused on December 1, 2021 to April 30, 2022.
  • A geopolitical risk sentiment time series was built from tweet data.
  • Granger causality found predictive information for several financial assets and markets.
  • The abstract does not name the specific assets or markets involved.

Disclosure

Research title:
Geopolitical risk sentiment predicted some market changes
Authors:
John Burns, Tom Kelsey, Carl Donovan
Institutions:
University of St Andrews, University of St Andrews, University of St Andrews
Publication date:
2026-02-25
DOI:
10.5750/jpm.v19i2.2322
OpenAlex record:
View
AI provenance: This post was generated by gpt-5.4-mini (OpenAI). The original authors did not write or review this post.