Skip to main content

LUP Student Papers

LUND UNIVERSITY LIBRARIES

The Impact of Public Sentiment During Corporate Crisis on Stock Price Movement

Choosri, Methawee LU (2025) DABN01 20251
Department of Economics
Department of Statistics
Abstract
The relationship between public sentiment and stock price fluctuations during corporate crises has attracted increasing attention in recent years. This study investigates the influence of public sentiment on stock price movements during a corporate crisis by integrating natural language processing of social media data,  time series analysis and machine learning predictive model. Sentiment classification was performed using a fine-tuned WangchanBERTa model on social media posts, while topic modelling with Latent Dirichlet Allocation (LDA) explored evolving public discourse throughout the crisis. Correlation analyses were then applied to identify potential relationships between sentiment and stock prices. Based on these insights, predictive... (More)
The relationship between public sentiment and stock price fluctuations during corporate crises has attracted increasing attention in recent years. This study investigates the influence of public sentiment on stock price movements during a corporate crisis by integrating natural language processing of social media data,  time series analysis and machine learning predictive model. Sentiment classification was performed using a fine-tuned WangchanBERTa model on social media posts, while topic modelling with Latent Dirichlet Allocation (LDA) explored evolving public discourse throughout the crisis. Correlation analyses were then applied to identify potential relationships between sentiment and stock prices. Based on these insights, predictive models, including regression and tree-based methods, were then developed using features derived from lagged sentiment and market indicators, providing valuable insights into stock price dynamics during crisis periods. (Less)
Please use this url to cite or link to this publication:
author
Choosri, Methawee LU
supervisor
organization
course
DABN01 20251
year
type
H1 - Master's Degree (One Year)
subject
keywords
sentiment analysis, machine learning, natural language processing, correlation analysis, topic modeling
language
English
id
9192462
date added to LUP
2025-09-12 09:03:45
date last changed
2025-09-12 09:03:45
@misc{9192462,
  abstract     = {{The relationship between public sentiment and stock price fluctuations during corporate crises has attracted increasing attention in recent years. This study investigates the influence of public sentiment on stock price movements during a corporate crisis by integrating natural language processing of social media data,  time series analysis and machine learning predictive model. Sentiment classification was performed using a fine-tuned WangchanBERTa model on social media posts, while topic modelling with Latent Dirichlet Allocation (LDA) explored evolving public discourse throughout the crisis. Correlation analyses were then applied to identify potential relationships between sentiment and stock prices. Based on these insights, predictive models, including regression and tree-based methods, were then developed using features derived from lagged sentiment and market indicators, providing valuable insights into stock price dynamics during crisis periods.}},
  author       = {{Choosri, Methawee}},
  language     = {{eng}},
  note         = {{Student Paper}},
  title        = {{The Impact of Public Sentiment During Corporate Crisis on Stock Price Movement}},
  year         = {{2025}},
}