Details

Autor(en) / Beteiligte

• Clarke, Jonathan
• Chen, Hailiang
• Du, Ding
• Hu, Yu Jeffrey

Titel

Fake News, Investor Attention, and Market Reaction

Ist Teil von

• Information systems research, 2021-03, Vol.32 (1), p.35-52

Ort / Verlag

Linthicum: INFORMS

Erscheinungsjahr

2021

Link zum Volltext

Quelle

Informs PubsOnline

Beschreibungen/Notizen

• Does fake news in financial markets attract more investor attention and have a significant impact on stock prices? The authors use the SEC crackdown of stock promotion schemes in April 2017 to examine investor attention and the stock price reaction to fake news articles. Using data from Seeking Alpha, the authors find that fake news stories generate significantly more attention than a control sample of legitimate articles. The authors find no evidence that article commenters can detect fake news, and they find that Seeking Alpha editors have only modest ability to detect fake news. However, the authors implement several well-known machine learning algorithms based on linguistic characteristics and show that machine learning algorithms can successfully identify fake news. In addition, the stock market appears to price fake news correctly. While abnormal trading volume increases around the release of fake news, the increase is less than that observed for legitimate news. The stock price reaction to fake news is discounted when compared with legitimate news articles. Does fake news in financial markets attract more investor attention and have a significant impact on stock prices? We use the U.S. Securities and Exchange Commission (SEC) crackdown of stock promotion schemes in April 2017 to examine investor attention and the stock price reaction to fake news articles. Using data from Seeking Alpha, we find that fake news stories generate significantly more attention than a control sample of legitimate articles. We find no evidence that article commenters can detect fake news, and we also find that Seeking Alpha editors have only modest ability to detect fake news. However, we show that machine learning algorithms can successfully identify fake news from linguistic features of the article. The stock market appears to price fake news correctly. While abnormal trading volume increases around the release of fake news, the increase is less than that observed for legitimate news. The stock price reaction to fake news is discounted when compared with legitimate news articles.