Finding Stocks with the highest Price/Tweet Sentiment Correlation
For a while I wanted to explore the relationship between social media sentiment and price trends. However, historical social media data is notoriously difficult or expensive to acquire.
I recently found a way to get my hands on already processed tweet sentiments using the EOD Data Tweet Sentiment API. This data is available with the ‘EOD Data — All World Plan’ for $19.99 a month — not too pricy.
In this post I’d like to present an overview of an approach on how to perform this analysis and then look at some of the results of my study.
This story is solely for general information purposes, and should not be relied upon for trading recommendations or financial advice. Source code and information is provided for educational purposes only, and should not be relied upon to make an investment decision. Please review my full cautionary guidance before continuing.
The Game Plan
First we need to narrow down the number of stocks we want to analyze in order to cut down processing time. In this post I decided to use the NASDAQ 100 index since that gives us a manageable number of work with.
Here are the steps we are going to implement:
- Load NASDAQ 100 list and for every stock:
