Work

Fake news and financial market volatility: A causal inference approach using high-frequency data

Year: 2026
Type: article
Abstract: Fake news about publicly listed companies is widely suspected to disrupt financial markets, but rigorous causal evidence remains scarce. This paper provides such evidence using a large novel dataset: 293 million firm-minute trading observations for S&P 500 constituents over 2018–2023, matched to 28,491 machine-classified fake news shock episodes drawn from more than 5.9 million Twitter/X and Facebook posts. We find that directly targeted firms experience a 16–24% increase in intraday realized volatility and a 9–17% widening of bid–ask spreads relative to otherwise similar firms. The effects appear within minutes, peak five to ten minutes after the shock, and largely revert within 90 min, although reversion is markedly slower for lower-capitalization firms and in periods of elevated market stress. Effects are roughly three times larger for small-cap firms than for higher-capitalization firms and are strongest for emotionally negative narratives. These findings are consistent with fake news operating simultaneously as a noise shock, an information-asymmetry shock, and a liquidity shock, and they carry implications for option pricing, portfolio risk management, market surveillance, and the regulation of online platforms and of disinformation more broadly.
Language: English
Subfield: Finance
Open Access status: gold
Estimated APC paid: $1,180
OpenAlex ID: W7226003015
FWCI:
Cites: 33
Cited by:
Related to: 10