Sentiment Analysis with VADER and LM Using Linear Regression for Stock Market Prediction

Xiaotong Luo

2024

Abstract

With the increasing popularity of stock trading, more and more researchers are focusing on stock prediction with various machine-learning models. In addition, a growing number of individual investors prefer to share their views on social media. As a result, market sentiment can influence the price of a stock. This paper is going to talk about creating a model with two sentiment lexicons (VADER and LM) that is trained with a linear regression algorithm and observing a relation between sentiment and real stock prices exists, especially for some technology tickers. However, in this article, the Pearson correlation coefficient p-value of some tickers is not statistically significant at a 95% confidence interval, which means the model do perform not well in the whole dataset. The reason may be the limitations of the algorithm for splitting train and test data or training models. Moving forward, the research intends to improve the method through feature engineering and model selection in the future.

Paper Citation

in Harvard Style

Luo X. (2024). Sentiment Analysis with VADER and LM Using Linear Regression for Stock Market Prediction. In Proceedings of the 1st International Conference on E-commerce and Artificial Intelligence - Volume 1: ECAI; ISBN 978-989-758-726-9, SciTePress, pages 33-38. DOI: 10.5220/0013205600004568

in Bibtex Style

@conference{ecai24,
author={Xiaotong Luo},
title={Sentiment Analysis with VADER and LM Using Linear Regression for Stock Market Prediction},
booktitle={Proceedings of the 1st International Conference on E-commerce and Artificial Intelligence - Volume 1: ECAI},
year={2024},
pages={33-38},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013205600004568},
isbn={978-989-758-726-9},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 1st International Conference on E-commerce and Artificial Intelligence - Volume 1: ECAI
TI - Sentiment Analysis with VADER and LM Using Linear Regression for Stock Market Prediction
SN - 978-989-758-726-9
AU - Luo X.
PY - 2024
SP - 33
EP - 38
DO - 10.5220/0013205600004568
PB - SciTePress