Using Stock Prices as Ground Truth in Sentiment Analysis to Generate
Profitable Trading Signals
E. Birbeck, and D. Cliff. (2018)cite arxiv:1811.02886Comment: 8 pages, 6 figures. To be presented at IEEE Symposium on Computational Intelligence in Financial Engineering (CIFEr), Bengaluru, November 18-21, 2018.
Abstract
The increasing availability of "big" (large volume) social media data has
motivated a great deal of research in applying sentiment analysis to predict
the movement of prices within financial markets. Previous work in this field
investigates how the true sentiment of text (i.e. positive or negative
opinions) can be used for financial predictions, based on the assumption that
sentiments expressed online are representative of the true market sentiment.
Here we consider the converse idea, that using the stock price as the
ground-truth in the system may be a better indication of sentiment. Tweets are
labelled as Buy or Sell dependent on whether the stock price discussed rose or
fell over the following hour, and from this, stock-specific dictionaries are
built for individual companies. A Bayesian classifier is used to generate stock
predictions, which are input to an automated trading algorithm. Placing 468
trades over a 1 month period yields a return rate of 5.18%, which annualises to
approximately 83% per annum. This approach performs significantly better than
random chance and outperforms two baseline sentiment analysis methods tested.
Description
Using Stock Prices as Ground Truth in Sentiment Analysis to Generate Profitable Trading Signals
cite arxiv:1811.02886Comment: 8 pages, 6 figures. To be presented at IEEE Symposium on Computational Intelligence in Financial Engineering (CIFEr), Bengaluru, November 18-21, 2018
%0 Generic
%1 birbeck2018using
%A Birbeck, Ellie
%A Cliff, Dave
%D 2018
%K quantfinance twitter
%T Using Stock Prices as Ground Truth in Sentiment Analysis to Generate
Profitable Trading Signals
%U http://arxiv.org/abs/1811.02886
%X The increasing availability of "big" (large volume) social media data has
motivated a great deal of research in applying sentiment analysis to predict
the movement of prices within financial markets. Previous work in this field
investigates how the true sentiment of text (i.e. positive or negative
opinions) can be used for financial predictions, based on the assumption that
sentiments expressed online are representative of the true market sentiment.
Here we consider the converse idea, that using the stock price as the
ground-truth in the system may be a better indication of sentiment. Tweets are
labelled as Buy or Sell dependent on whether the stock price discussed rose or
fell over the following hour, and from this, stock-specific dictionaries are
built for individual companies. A Bayesian classifier is used to generate stock
predictions, which are input to an automated trading algorithm. Placing 468
trades over a 1 month period yields a return rate of 5.18%, which annualises to
approximately 83% per annum. This approach performs significantly better than
random chance and outperforms two baseline sentiment analysis methods tested.
@misc{birbeck2018using,
abstract = {The increasing availability of "big" (large volume) social media data has
motivated a great deal of research in applying sentiment analysis to predict
the movement of prices within financial markets. Previous work in this field
investigates how the true sentiment of text (i.e. positive or negative
opinions) can be used for financial predictions, based on the assumption that
sentiments expressed online are representative of the true market sentiment.
Here we consider the converse idea, that using the stock price as the
ground-truth in the system may be a better indication of sentiment. Tweets are
labelled as Buy or Sell dependent on whether the stock price discussed rose or
fell over the following hour, and from this, stock-specific dictionaries are
built for individual companies. A Bayesian classifier is used to generate stock
predictions, which are input to an automated trading algorithm. Placing 468
trades over a 1 month period yields a return rate of 5.18%, which annualises to
approximately 83% per annum. This approach performs significantly better than
random chance and outperforms two baseline sentiment analysis methods tested.},
added-at = {2018-11-09T05:46:51.000+0100},
author = {Birbeck, Ellie and Cliff, Dave},
biburl = {https://www.bibsonomy.org/bibtex/25bd5641460528a7f972d3acb0a6421d0/shabbychef},
description = {Using Stock Prices as Ground Truth in Sentiment Analysis to Generate Profitable Trading Signals},
interhash = {bab1bfc2f682618c8425283c1555e7bb},
intrahash = {5bd5641460528a7f972d3acb0a6421d0},
keywords = {quantfinance twitter},
note = {cite arxiv:1811.02886Comment: 8 pages, 6 figures. To be presented at IEEE Symposium on Computational Intelligence in Financial Engineering (CIFEr), Bengaluru, November 18-21, 2018},
timestamp = {2018-11-09T05:46:51.000+0100},
title = {Using Stock Prices as Ground Truth in Sentiment Analysis to Generate
Profitable Trading Signals},
url = {http://arxiv.org/abs/1811.02886},
year = 2018
}