Although this algorithm isn't ready to conquer the stock market world, it has shown that both supervised and unsupervised machine learning algorithms have the ability to predict stock market trends based on social media data to a reasonable degree.
For future expansions of this project, I would like to vastly increase the size of the dataset used, experiment with other dimensions such as graph theory based evaluation of the network, explore using more than one social media source, and just play with this concept on a larger scale.
However, there is only so much you can do in this short a time.
A full link to the code can be accessed on the side menu at the Github link
This website was made using pelican and markdown, which are great python website-building resources that too many people don't know about so check them out at the footer.
If you would like to get in contact with me for any reason, click the Facebook, or email links on the side menu.
A HUGE thanks to the sponsors and student for putting together a great hackathon and all the people who graciously posted on stackoverflow answers to questions I had along the way.
Thanks for reading my project blog - Wesley Klock #hackUTD2018