Do News and Sentiment play a role in Stock Price Prediction?

Bruce J Vanstone, Adrian Gepp, Geoffrey Harris

Research output: Contribution to journalArticleResearchpeer-review

Abstract

Despite continuous improvement in the range and quality of machine learning techniques, accurately predicting stock prices still remains as elusive as ever. We approach this problem using a modern autoregressive neural network architecture and incorporate sentiment predictors, which are becoming increasingly available due to advances in text mining techniques. We find that the inclusion of predictors based on counts of the number of news articles and twitter posts can significantly improve the quality of stock price predictions.
Original languageEnglish
Pages (from-to)3815-3820
Number of pages6
JournalApplied Intelligence
Volume49
Issue number11
Early online date9 Apr 2019
DOIs
Publication statusPublished - 1 Nov 2019

Fingerprint

Network architecture
Learning systems
Neural networks

Cite this

@article{fd7a7363f0754fe1aa62bd7e4fc5e30d,
title = "Do News and Sentiment play a role in Stock Price Prediction?",
abstract = "Despite continuous improvement in the range and quality of machine learning techniques, accurately predicting stock prices still remains as elusive as ever. We approach this problem using a modern autoregressive neural network architecture and incorporate sentiment predictors, which are becoming increasingly available due to advances in text mining techniques. We find that the inclusion of predictors based on counts of the number of news articles and twitter posts can significantly improve the quality of stock price predictions.",
author = "Vanstone, {Bruce J} and Adrian Gepp and Geoffrey Harris",
year = "2019",
month = "11",
day = "1",
doi = "10.1007/s10489-019-01458-9",
language = "English",
volume = "49",
pages = "3815--3820",
journal = "Applied Intelligence",
issn = "0924-669X",
publisher = "Springer",
number = "11",

}

Do News and Sentiment play a role in Stock Price Prediction? / Vanstone, Bruce J; Gepp, Adrian; Harris, Geoffrey.

In: Applied Intelligence, Vol. 49, No. 11, 01.11.2019, p. 3815-3820.

Research output: Contribution to journalArticleResearchpeer-review

TY - JOUR

T1 - Do News and Sentiment play a role in Stock Price Prediction?

AU - Vanstone, Bruce J

AU - Gepp, Adrian

AU - Harris, Geoffrey

PY - 2019/11/1

Y1 - 2019/11/1

N2 - Despite continuous improvement in the range and quality of machine learning techniques, accurately predicting stock prices still remains as elusive as ever. We approach this problem using a modern autoregressive neural network architecture and incorporate sentiment predictors, which are becoming increasingly available due to advances in text mining techniques. We find that the inclusion of predictors based on counts of the number of news articles and twitter posts can significantly improve the quality of stock price predictions.

AB - Despite continuous improvement in the range and quality of machine learning techniques, accurately predicting stock prices still remains as elusive as ever. We approach this problem using a modern autoregressive neural network architecture and incorporate sentiment predictors, which are becoming increasingly available due to advances in text mining techniques. We find that the inclusion of predictors based on counts of the number of news articles and twitter posts can significantly improve the quality of stock price predictions.

UR - http://www.scopus.com/inward/record.url?scp=85074338760&partnerID=8YFLogxK

U2 - 10.1007/s10489-019-01458-9

DO - 10.1007/s10489-019-01458-9

M3 - Article

VL - 49

SP - 3815

EP - 3820

JO - Applied Intelligence

JF - Applied Intelligence

SN - 0924-669X

IS - 11

ER -