Stock Movement Prediction Based on Social Media Sentiment Analysis

Dodevski, Aleksandar and Koceska, Natasa and Koceski, Saso (2018) Stock Movement Prediction Based on Social Media Sentiment Analysis. Journal of Applied Economics and Business. ISSN 1857 - 8721

[img]
Preview
Text
SK 1.pdf

Download (654Kb) | Preview
Official URL: http://www.aebjournal.org/article060303.php

Abstract

Stock prediction is attracting a lot of attention, mainly due the financial gains that may be obtained. However, this is very difficult task and it is very challenging problem that intrigues multiple scientific disciplines such as finance, computer sciences as well as engineering and mathematics. There are many approaches and theories regarding stock movement prediction. In the era of social network and big data, as well as huge speed of news spreading, probably the most interesting are those theories based on social media sentiment analysis. This approach is taking as input non quantifiable data such as financial news articles, social networks posts, or tweeter messages, about a company and predicting its future stock trend with news sentiment classification. Sentiment classification is performed using artificial intelligence algorithms. Main aim of this paper is to give a comprehensive review of current state of the art related to stock movement prediction based on social media sentiment analysis with an emphasis on a Twitter platform.

Item Type: Article
Subjects: Natural sciences > Computer and information sciences
Divisions: Faculty of Computer Science
Depositing User: Natasa Koceska
Date Deposited: 21 Jan 2019 09:24
Last Modified: 21 Jan 2019 09:24
URI: http://eprints.ugd.edu.mk/id/eprint/21174

Actions (login required)

View Item View Item