• A new stock market forecasting model utilizing sentiment analysis and attention mechanism is presented in this paper to forecast AAPL during the COVID-19 pandemic
• Scraped tweets from the Stock investing community Stocktwits and developed a Bidirectional LSTM with GloVe word embeddings to predict whether the tweet is bullish or bearish
• Developed an LSTM with an attention mechanism and sentiments from the text classifier to forecast stock market prices across 2020
• Stock market sentiment analyzer reached accuracy of 74% (5% higher than previous papers) and LSTM model with sentiment analysis and attention mechanism increased R-squared by over 10% from the baseline LSTM
• Accepted into 2021 IEEE 5th Advanced Information Technology, Electronic and Automation Control Conference on the Big Data track
-
Notifications
You must be signed in to change notification settings - Fork 1
BabyChouSr/TweetStock
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Folders and files
Name | Name | Last commit message | Last commit date | |
---|---|---|---|---|
Repository files navigation
About
Utilizes GloVe embeddings to classify tweets and create sentiment indexes, which allows an LSTM to forecast stock closing prices
Topics
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published