Year: 2007
Type: conference-paper
Abstract: Text is not unadulterated fact. A text can \nmake you laugh or cry but can it also make\nyou short sell your stocks in company A and\nbuy up options in company B? Research in\nthe domain of finance strongly suggests that\nit can. Studies have shown that both the\ninformational and affective aspects of news\ntext affect the markets in profound ways, impacting on volumes of trades, stock prices,\nvolatility and even future firm earnings. This paper aims to explore a computable metric of positive or negative polarity in financial news text which is consistent with human judgments and can be used in a quantitative analysis of news sentiment impact on financial markets. Results from a preliminary evaluation are presented and discussed.
Authors: Ann Devitt, Khurshid Ahmad
Institution: Trinity College Dublin
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W2128279859