Sentiment and stock market volatility predictive modelling — A hybrid approach

Olaniyan, Rapheal; Stamate, Daniel; Ouarbya, Lahcen; Logofătu, Doina

doi:10.1109/dsaa.2015.7344855

Cited by 7 publications

(4 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In contrast to the excess returns model, both measurements of sentiment appear to have an effect on daily volatility in the FTSE 100. These results are consistent with the literature, with negative sentiment increasing volatility (Kumari and Mahakud 2015;Lee, Jiang, and Indro 2002) and showing greater statistical significance than positive sentiment (Wu, Zheng, and Olson 2014), which reduces volatility (Kumari and Mahakud 2015;Lee, Jiang, and Indro 2002;Olaniyan et al 2017). Overall, the results suggest that while the activity of retail investors based on sentiment doesn't influence market returns, their behaviour does add significant noise to the market.…”

Section: Analysis Of Statistical Significancesupporting

confidence: 90%

“…Additionally, measures of investor sentiment have been shown to influence volatility in asset prices (Antweiler and Frank 2004; Da, Engelberg, and Gao 2015; Grob-Klubmann and Hautsch 2011; Kumari and Mahakud 2015;Lee, Jiang, and Indro 2002;Olaniyan et al 2017;Tetlock 2007;Wu, Zheng, and Olson 2014). The literature suggests that positive sentiment decreases volatility (Kumari and Mahakud 2015;Lee, Jiang, and Indro 2002;Olaniyan et al 2017), while negative sentiment increases volatility (Kumari and Mahakud 2015;Lee, Jiang, and Indro 2002). It has also been reported that negative sentiment has higher predictive power than positive sentiment (Wu, Zheng, and Olson 2014).…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Predicting FTSE 100 returns and volatility using sentiment analysis

Johnman

Vanstone

Gepp

2018

Accounting & Finance

View full text Add to dashboard Cite

We investigate the statistical and economic effect of positive and negative sentiment on daily excess returns and volatility in the FTSE 100 index, using business news articles published by the Guardian Media Group between 01/01/2000 and 01/06/2016. The analysis indicates that while business news sentiment derived from articles aimed at retail traders doesn't influence excess returns in the FTSE 100 index, it does affect volatility, with negative sentiment increasing volatility and positive sentiment reducing it. Further, an ETF-based trading strategy based on these findings is found to outperform the naïve buy-and-hold approach.

show abstract

Section: Analysis Of Statistical Significancesupporting

confidence: 90%

Section: Resultsmentioning

confidence: 99%

Predicting FTSE 100 returns and volatility using sentiment analysis

Johnman

Vanstone

Gepp

2018

Accounting & Finance

View full text Add to dashboard Cite

show abstract

“…Third, the researchers used i) a non-parametric and nonlinear approach and ii) a hybrid GARCH coupled with artificial neural networks (NN) to test the prediction power of the positive and negative sentiments. As a final experiment, Olaniyan et al [8] explored the predictive power of sentiment on volatility Qt. They used an EGARCH lagged volatilities Qt-1 and Qt-3, coupled with the positive and negative sentiment Pt-1, Pt-2 and Nt-1, Nt-2 as attribute variables into a feed-forward NN, a Jordan and an Elman recursive NN.…”

Section: Introductionmentioning

confidence: 99%

On XLE Index Constituents’ Social Media Based Sentiment Informing the Index Trend and Volatility Prediction

Marechal

Stamate

Olaniyan

et al. 2018

Computational Collective Intelligence

Self Cite

View full text Add to dashboard Cite

Collective intelligence represented as sentiment extracted from social media mining found applications in various areas. Numerous studies involving machine learning modelling have demonstrated that such sentiment information may or may not have predictive power on the stock market trend. This research investigates the predictive information of sentiment regarding the Energy Select Sector related XLE index and of its constituents, on the index and its volatility, based on a novel robust machine learning approach. While we demonstrate that sentiment does not have any impact on any of the trend prediction scenarios investigated here related to XLE and its constituents, the sentiment's impact on volatility predictions is significant. The proposed volatility prediction modelling approach, based on Jordan and Elman recurrent neural networks, demonstrates that the addition of sentiment or sentiment moment reduces the prediction root mean square error (RMSE) to about one third. The experiments we conducted also demonstrate that the addition of sentiment reduces the RMSE for 24 out of the 36 stocks/constituents, representing 87.9% of the index weight. This is the first study in the literature relating to the prediction of the market trend or the volatility based on an index and its constituents' sentiment.

show abstract

“…Dataset: hotel reviews from Trip Advisor, beer reviews from Rate Beer and app reviews applause. Olaniyan, Rapheal et al [9] Assesses the stock market returns influence of sentiment prediction by using a nonlinear non-parametric approach which corrects specific borders further it proposes a new method in developing volatility stock market models of prediction by integrating a hybrid GARCH and framework of artificial neural network. Dataset used is 500 index values of S&P from September 6th 2012 to may 12th 2014 stock market data.…”

Section: Literature Reviewmentioning

confidence: 99%

A Panoptics of Sentimental Analysis

Kallipalli

Sridhar²,

Vijayalakshmi³

2017

ijarcs

View full text Add to dashboard Cite

Sentiment Analysis(SA) persist to be a most significant research problem due to its immense applications, recognize the sentiment orientation of terms of sentiment which is the sentiment analysis fundamental task. Sentiment Analysis is a computational treatment of opinions and subjectivity of text focuses on either short/long range syntactic or semantic dependencies. Nowadays decision making is very much impacted by the products and services reviews of the products/item, these review data can be used to define trends over time. Sentimental analysis of Text data available in different forms of blogs, twitters, Facebook and Linked-in offers information to assess perspective of services of people's, products that are of their interest, items information in which they are having interested in purchasing. Locating document carrying positive/negative favourability and the information gained by the sentimental analysis supports in improving the services and products and in turn in decision making to add an augmented edge over their competitors in the business, it can also be used in cycle with effectual visualizations to calculate and track emotions. In this paper we present a comprehensive review of model and recent trend of research used in implementation of sentimental analysis.

show abstract

Sentiment and stock market volatility predictive modelling — A hybrid approach

Cited by 7 publications

References 21 publications

Predicting FTSE 100 returns and volatility using sentiment analysis

Predicting FTSE 100 returns and volatility using sentiment analysis

On XLE Index Constituents’ Social Media Based Sentiment Informing the Index Trend and Volatility Prediction

A Panoptics of Sentimental Analysis

Contact Info

Product

Resources

About