Back to search

Institutional Repository of Vilnius University

Melagingų naujienų ir bendrovių vadovų viešų pasisakymų poveikis žiniasklaidos emociniam tonui ir akcijų kainai /

Abstract

dc:description

This work examines the interaction between the emotional tone of the media and the stock price fluctuations of two global market leaders – Tesla and Meta. The study investigates and analyzes how the sentiments conveyed by the media, including fake news and controversial statements by executives, affect the companies' stock price indicators and shape the perception of investors. Problem: To what extent does the emotional tone of the media influence stock prices and how is this relationship modified by external and internal factors? Objective: To evaluate the relationship and causal connection between the emotional tone of the media and changes in the companies' stock closing prices, as well as identify and analyze factors such as fake news and controversial statements by company executives that could influence media sentiments. Tasks: 1. Gather all the necessary data for the study: Use Python programming language to extract headlines about the analyzed companies and their adjusted daily closing stock prices for the selected analysis period; 2. Employ a machine learning model to analyze the sentiment of the extracted headlines, generating composite sentiment scores to be used in further analysis; 3. Prepare the sentiment scores and stock closing price data for statistical analysis by processing them into monthly averages and creating graphical visualizations for the analyzed period; 4. Conduct cross-correlation analysis and Granger causality tests for both companies to identify the relationships between media sentiment and the monthly averages of stock closing prices; 5. Perform a factor analysis for both cases to determine the association between false news and controversial statements by company executives with media sentiment, the monthly averages of stock closing prices, and their relationship; 6. Present conclusions and practical recommendations based on the study results and the insights obtained. Research methods used: The study employed a combination of quantitative and qualitative methods. The quantitative analysis included cross-correlation analysis and the Granger causality test to determine the statistical relationship between media sentiment scores and changes in the monthly averages of stock closing prices during the period from January 2019 to October 2024. The qualitative analysis focused on assessing the impact of false news and executive statements on media sentiment, the monthly averages of stock closing prices, and their interrelation. For the study, Tesla and Meta were selected as innovative companies that frequently attract media attention. Results obtained: Using cross-correlation analysis and the Granger causality test, it was determined that changes in sentiment analysis often have a significant impact on stock price dynamics within the first few months. In the case of Tesla, changes in average sentiment show a limited effect on stock price fluctuations, especially over longer periods, indicating the company's ability to effectively manage misinformation. In contrast, Meta demonstrated a stronger relationship between sentiment changes and stock prices, revealing a greater vulnerability of the company to the impact of misinformation. Conclusions: The analysis of media sentiment scores and the closing stock prices of Tesla and Meta revealed different trends for both companies. In the case of Tesla, media sentiment has limited predictive value for stock price changes, as well as the impact of controversial statements and fake news on the relationship between sentiment and stock prices was minimal. However, for Meta sentiment analysis strongly correlated with stock price analysis in the short term, but this relationship was more disrupted by the spread of disinformation related to reputation and trust issues. Consequently, it was observed that Tesla responds more promptly and effectively to disinformation compared to Meta.

Degree

thesis:*
Grantor dc:publisher
Institutional Repository of Vilnius University
Year dc:date
2025

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Čigileičikaitė, Laura,

Rights

dc:rights
Statement dc:rights
  • info:eu-repo/semantics/openAccess
Language dc:language
lit

Identifiers

dc:identifier.*

Chain of custody

source
Harvested from
Vilnius University
Base URL
epublications.vu.lt/oai
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
related terms
citation

Čigileičikaitė, Laura,. Melagingų naujienų ir bendrovių vadovų viešų pasisakymų poveikis žiniasklaidos emociniam tonui ir akcijų kainai /. Institutional Repository of Vilnius University, 2025. https://repository.vu.lt/VU:ELABAETD229555751&prefLang=en_US