2015
DOI: 10.1371/journal.pone.0138441
|View full text |Cite
|
Sign up to set email alerts
|

The Effects of Twitter Sentiment on Stock Price Returns

Abstract: Social media are increasingly reflecting and influencing behavior of other complex systems. In this paper we investigate the relations between a well-known micro-blogging platform Twitter and financial markets. In particular, we consider, in a period of 15 months, the Twitter volume and sentiment about the 30 stock companies that form the Dow Jones Industrial Average (DJIA) index. We find a relatively low Pearson correlation and Granger causality between the corresponding time series over the entire time perio… Show more

Help me understand this report
View preprint versions

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

9
188
0
8

Year Published

2016
2016
2022
2022

Publication Types

Select...
9

Relationship

0
9

Authors

Journals

citations
Cited by 277 publications
(205 citation statements)
references
References 57 publications
9
188
0
8
Order By: Relevance
“…Naive Bayes or Support Vector Machines) are applied to extract sentiment based on supervised learning (i.e. a labeled/ annotated training data set are required to build this classification model).Yet, the manual annotation and cross-validation of this data set that are required to obtain reliable labeled tweets is highly expensive and time-consuming (Ranco, Aleksovski, Caldarelli, Grcar, & Mozetic, 2015;Oliveira et al, 2017).…”
Section: Methodsological Considerationsmentioning
confidence: 99%
See 1 more Smart Citation
“…Naive Bayes or Support Vector Machines) are applied to extract sentiment based on supervised learning (i.e. a labeled/ annotated training data set are required to build this classification model).Yet, the manual annotation and cross-validation of this data set that are required to obtain reliable labeled tweets is highly expensive and time-consuming (Ranco, Aleksovski, Caldarelli, Grcar, & Mozetic, 2015;Oliveira et al, 2017).…”
Section: Methodsological Considerationsmentioning
confidence: 99%
“…In a similar study, Ranco et al (2015) examine the relationship between Twitter activity and sentiment and stock returns for a sample of the 30 constituent firms of the Dow Jones Industrial Average (DJIA) index. The sample used consists of 1.5 million tweets collected about the sample firms during the period (2013)(2014).…”
Section: Twitter Sentiment/information and Stock Market Performancementioning
confidence: 99%
“…For instance, [42] investigated a 15-month period of Twitter data including sentiment, concerning 30 stock companies registered on the Dow Jones Industrial Average (DJIA) index. This work gave some insights about sentiment and abnormal returns during the peaks of Twitter volume.…”
Section: Twitter As a Source For Decision Makingmentioning
confidence: 99%
“…Still, other forms of high-speed financial analysis are disrupting and transforming the marketplace. Firms like Neokami and Sentient now offer trading platforms using Big Data analytics that not only cover unusual order flow but, also, company reports, conference calls, and the sentiment and mood analysis of social media messages (Barberis, Shleifer, and Vishny, 1998;Brown & Cliff, 2004;Tetlock, 2007;Antweiler & Frank, 2004;Wurgler, 2007;Zhang, Fuehres, and Gloor, 2011;Kleinnijenhuis, Schultz, Oegema, and Van Atteveldt, 2013;Lee, Hutton, and Shu, 2015;Ranco, Aleksovski, Caldarelli, Grčar, and Mozetič, 2015). "We can analyze millions of variables within seconds and create a customized predictive model for any stock," says Ozel Christo, founder and CEO of Neokami.…”
Section: Big Data Analytics and Social Media Feedsmentioning
confidence: 99%