Predicting stock return volatility using sentiment analysis of corporate annual reports

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216275%3A25410%2F21%3A39917733" target="_blank" >RIV/00216275:25410/21:39917733 - isvavai.cz</a>

Result on the web

<a href="https://www.taylorfrancis.com/chapters/edit/10.4324/9781003037903-5/predicting-stock-return-volatility-using-sentiment-analysis-corporate-annual-reports-petr-hajek-renata-myskova-vladimir-olej" target="_blank" >https://www.taylorfrancis.com/chapters/edit/10.4324/9781003037903-5/predicting-stock-return-volatility-using-sentiment-analysis-corporate-annual-reports-petr-hajek-renata-myskova-vladimir-olej</a>

DOI - Digital Object Identifier

—

Result language

angličtina

Original language name

Predicting stock return volatility using sentiment analysis of corporate annual reports

Original language description

This chapter focuses on the short-term volatility of corporate stocks and the causes that triggered it, and derives implied volatility based on historical volatility. Chin et al. examined the links among stock market volatility, market sentiment, macroeconomic indicators, and spread volatility over the persisting long-term component and the temporary short-term component. They found no empirical evidence of the link between the volatile component and macroeconomic indicators but found that the intermediate component was linked to variations in market sentiment. The chapter aims to propose a machine learning-based model for predicting short-term stock return volatility and study the effect of annual report filing on abnormal changes in firms’ stock returns using the proposed model. It demonstrates that mining corporate annual reports can be effective in predicting short-term stock return volatility using a three-day event window.

Czech name

—

Czech description

—

Type

C - Chapter in a specialist book

CEP classification

—

OECD FORD branch

50206 - Finance

Project

<a href="/en/project/GA19-15498S" target="_blank" >GA19-15498S: Modelling emotions in verbal and nonverbal managerial communication to predict corporate financial risk</a><br>

Continuities

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Publication year

2021

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Book/collection name

Essentials of Machine Learning in Finance and Accounting

ISBN

978-0-367-48083-7

Number of pages of the result

21

Pages from-to

75-95

Number of pages of the book

258

Publisher name

Taylor &amp; Francis Ltd.

Place of publication

Abingdon

UT code for WoS chapter

—