Open AccessIDENTIFICATION OF NEWS TEXT CORPORA INFLUENCING THE VOLATILITY OF FINANCIAL INSTRUMENTS
Author(s) -
A. Stankus
Publication year - 2021
Publication title -
9th international conference "distributed computing and grid technologies in science and education"
Language(s) - English
Resource type - Conference proceedings
DOI - 10.54546/mlit.2021.55.62.001
Subject(s) - volatility (finance) , financial market , computer science , artificial neural network , task (project management) , identification (biology) , implied volatility , data science , artificial intelligence , econometrics , finance , business , economics , botany , management , biology
Using neural networks to predict changes in financial markets is a promising task. For more accurateforecasting, it is necessary to determine the tone of the texts of the articles, whether the news carriespositive or negative information for the market. Standard approaches to using pretrained neuralnetworks aimed at analyzing user reviews are not successful due to the fact that professional reporterstry to present their articles in a neutral way, which leads to incorrect conclusions. In this article, wewill talk about the possibilities of training neural networks to analyze the sentiments of articles basedon volatility data in the volatility of financial markets.