Research Online

Logo

Goldsmiths - University of London

Social Web-based Anxiety Index's Predictive Information on S&P 500 Revisited

Olaniyan, Rapheal; Stamate, Daniel and Logofatu, Doina. 2015. 'Social Web-based Anxiety Index's Predictive Information on S&P 500 Revisited'. In: SLDS 2015: 3rd International Syposium on Statistical Learning and Data Sciences. Royal Holloway UoL, Egham, United Kingdom. [Conference or Workshop Item]

[img]
Preview
Text
SLDS.pdf

Download (98kB) | Preview

Abstract or Description

There has been an increasing interest recently in examining
the possible relationships between emotions expressed online and stock markets. Most of the previous studies claiming that emotions have predictive influence on the stock market do so by developing various machine learning predictive models, but do not validate their claims rigorously by analysing the statistical significance of their findings. In turn, the few works that attempt to statistically validate such claims suffer from important limitations of their statistical approaches. In particular, stock market data exhibit erratic volatility, and this time-varying volatility makes any possible relationship between these variables non-linear, which tends to statistically invalidate linear based approaches. Our work tackles this kind of limitations, and extends linear frameworks by proposing a new, non-linear statistical approach that accounts for non-linearity and heteroscedasticity.

Item Type:

Conference or Workshop Item (Paper)

Keywords:

Data Science, Machine Learning, Statistical Learning, Financial Forecasting, Sentiment Analysis, Social Web Mining, Monte Carlo Simulation

Departments, Centres and Research Units:

Computing

Dates:

DateEvent
15 April 2015Published
19 December 2014Accepted

Event Location:

Royal Holloway UoL, Egham, United Kingdom

Item ID:

17649

Date Deposited:

05 Apr 2016 07:11

Last Modified:

17 May 2019 09:19

URI:

http://research.gold.ac.uk/id/eprint/17649

View statistics for this item...

Edit Record Edit Record (login required)