Michigan State University
MICROBLOG GUIDED CRYPTOCURRENCY TRADING AND FRAMING ANALYSIS
Abstract
dc:descriptionWith 56 million people actively trading and investing in cryptocurrency online and globally, there is an increasing need for an automatic social media analysis tool to help understand trading discourse and behavior. Previous works have shown the usefulness of modeling microblog discourse for the prediction of trading stocks and their price fluctuations, as well as content framing. In this work, I present a natural language modeling pipeline that leverages language and social network behaviors for the prediction of cryptocurrency day trading actions and their associated framing patterns. Specifically, I present two modeling approaches. The first determines if the tweets of a 24-hour period can be used to guide day trading behavior, specifically if a cryptocurrency investor should buy, sell, or hold their cryptocurrencies in order to make a trading profit. The second is an unsupervised deep clustering approach to automatically detect framing patterns. My contributions include the modeling pipeline for this novel task, a new dataset of cryptocurrency-related tweets from influential accounts, and a transaction volume dataset. The experiments executed show that this weakly-supervised trading pipeline achieves an 88.78% accuracy for day trading behavior predictions and reveals framing fluctuations prior to and during the COVID-19 pandemic that could be used to guide investment actions.
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Pawlicka Maule, Anna Paula
- Contributors dc:contributor
-
- Johnson, Kristen
- Kordjamshidi, Parisa
- Zhou, Jiayu
Subjects
dc:subject × 1Rights
dc:rights- Statement dc:rights
-
- In Copyright
- Language dc:language
- English
Identifiers
dc:identifier.*- Identifier
-
etd:49551
local:PawlickaMaule_grad.msu_0128N_18048