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

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.

Authors

Institutions

Publication Details

Journal
Social Sciences & Humanities Open
Published
2026-11-13
DOI
https://doi.org/10.1016/j.ssaho.2026.104037
Primary Topic
Financial Markets and Investment Strategies
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

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

Abdelhak Anajar, Mohamed Rahmo, Said Maizzou
Social Sciences & Humanities Open
Financial Markets and Investment Strategies
article

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

Abdelhak Anajar, Mohamed Rahmo, Said Maizzou
article en

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.

Social Sciences & Humanities OpenVol. 14
Université Hassan 1er (MA)
Financial Markets and Investment Strategies
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon