News vs. Sentiment: Predicting Stock Returns from News Stories

News vs. Sentiment: Predicting Stock Returns from News Stories

The authors used a dataset of more than 900,000 news stories to test whether news can predict stock returns. They measured sentiment with a proprietary Thomson Reuters neural network and found that daily news predicts stock returns for only one to two days, confirming previous research. Weekly news,...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Financial analysts journal 2017-01, Vol.73 (3), p.67-83
Hauptverfasser: Heston, Steven L., Sinha, Nitish Ranjan
Format: Artikel
Sprache:eng
Schlagworte:
Artificial intelligence
Codes
Datasets
Delayed
Earnings
Earnings announcements
Media coverage
Neural networks
News
Predictions
Rates of return
Securities markets
Social networks
Stock prices
Studies
Text analysis
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:The authors used a dataset of more than 900,000 news stories to test whether news can predict stock returns. They measured sentiment with a proprietary Thomson Reuters neural network and found that daily news predicts stock returns for only one to two days, confirming previous research. Weekly news, however, predicts stock returns for one quarter. Positive news stories increase stock returns quickly, but negative stories receive a long-delayed reaction. Much of the delayed response to news occurs around the subsequent earnings announcement.
ISSN:0015-198X
1938-3312
DOI:10.2469/faj.v73.n3.3