All Rights Reserved
AccessEcon LLC 2006, 2008.
Powered by MinhViet JSC
ralph lauren polo

 
Cuiyuan Wang, Tao Wang and Changhe Yuan
 
''Does Applying Deep Learning in Financial Sentiment Analysis Lead to Better Classification Performance?''
( 2020, Vol. 40 No.2 )
 
 
Using a unique data set from Seeking Alpha, we compare the deep learning approach with traditional machine learning approaches in classifying financial text. We apply the long short-term memory (LSTM) as the deep learning method and Naive Bayes, SVM, Logistic Regression, XGBoost as the traditional machine learning approaches. The results suggest that the LSTM model outperforms the conventional machine learning methods on all metrics. Based on the t-SNE graph, the success of the LSTM model is partially explained as the high-accuracy LSTM model distinguishes between positive and negative important sentiment words while those words are chosen based on SHAP values and also appear in the widely used financial word dictionary, the Loughran-McDonald Dictionary (2011).
 
 
Keywords: Machine Learning, Deep Learning, Financial Social Media, Sentiment Analysis, Long Short-Term Memory
JEL: C1 - Econometric and Statistical Methods: General
G1 - (G11, G13, G13) Portfolios, Investments, Asset and Futures Pricing, Trading Volume & Bond Interest Rates
 
Manuscript Received : Nov 17 2019 Manuscript Accepted : Apr 29 2020

  This abstract has been downloaded 33 times                The Full PDF of this paper has been downloaded 107296 times