Full Text Available
Note: Clicking the button above will open the full text document at the original institutional repository in a new window.
Stock Prediction using Natural Language Processing Sentiment Analysis on News Headlines During COVID-19
Stock prediction based on NLP sentiment analysis is one of the most researched topics due to the revenues they generate for investors. Researchers have used various tools to achieve this, especially fundamental and technical analysis based on historical data helped to achieve this target. Due to the...
Saved in:
| Main Author: | |
|---|---|
| Format: | Thesis |
| Published: |
AUC Knowledge Fountain
2021
|
| Subjects: | |
| Tags: |
No Tags, Be the first to tag this record!
|
| Summary: | Stock prediction based on NLP sentiment analysis is one of the most researched topics due to the revenues they generate for investors. Researchers have used various tools to achieve this, especially fundamental and technical analysis based on historical data helped to achieve this target. Due to the technological advancement and abundance of data, the introduction of machine learning tools accelerated that approach. However, as the public mood affects the stock market, the need for another analysis emerged. Natural language processing sentiment analysis on data from various sources was able to capture public events and moods. NLP is one of the most effective tools since covering the public moods, and capturing the sentiment is the main driver for stock markets. In this research, NLP sentiment analysis shall be applied to news to predict United States technology stock companies and indices during COVID-19 using a natural language toolkit. The contribution of this is the research is creating a model for predicting the technology companies listed in the United States market during the crisis. The model is achieving over 61% accuracy and could be highly improved by adding other resources of news. |
|---|