Finding Expert Authors in Financial Forum Using Deep Learning Methods

Abstract

The modern stock market is a popular place to increase wealth and generate income, but the fundamental problem of when to buy or sell shares, or which stocks to buy has not been solved. It is very common among investors to have professional financial advisers, but what is the best resource to support the decisions these people make? Investment banks, such as Goldman Sachs, Lehman Brothers, and Salomon Brothers have dominated the world of financial advice for decades. However, due to the popularity of the Internet and financial social networks, such as StockTwits and Seeking Alpha, investors around the world have a new opportunity to gather and share their experiences. This raises new questions: is the information these users provide trustworthy? How can we find the experts? In this paper, we seek to determine if neural network models can help us find the experts in a set of StockTwits tweets. We applied two neural network models - doc2vec and convolutional neural networks - to find top authors in StockTwits based on their messages. Our results showed that a convolutional neural network is the best model to predict such top authors in this data set.