Uncertainty in Central and Eastern European markets. Evidence from Twitter-based uncertainty measures

Abstract

ABSTRACT Purpose Increasing uncertainty has frequently been associated with alterations in investor behaviour in scientific discourse. Central and Eastern Europe (CEE) despite generating 10% of the EU’s GDP, has largely been overlooked in investigations into the relationship between socialmedia uncertainty and its impact on the stock markets. The purpose of this article is to examine the dependence between the largest stock indices of the CEE markets and Twitter uncertainty measures. Design/methodology/approach The Vector Autoregressive (VAR) methodology, specifically bivariate Granger causality is applied to investigate the relationship between social media messages and market behaviour reflected in returns of the main stock indices for Croatian CROBEX, Czech PX, Hungarian BUX, Polish WIG and Romanian BET indices. Findings The author discovers substantial evidence indicating that the CEE region exhibits heterogeneity concerning its relationship with uncertainty in stock markets, with measures related to recession, political events, and natural disasters being of utmost relevance. Originality/value­ While the VAR model and Granger causality have been studied in relation to many markets, there is a lack of studies on the effect of Twitter-based wider spectrum of uncertainty measures on the CEE region. Twitter-based uncertainty measures on the CEE region represent a significant knowledge gap, that when addressed, could offer valuable insight into the region’s financial dynamics, thus potentially affecting hedging strategies, enhancing investor’s awareness and informing policy-making decisions.