A Novel Twitter Sentiment Analysis Model with Baseline Correlation for Financial Market Prediction with Improved Efficiency

Xinyi Guo; Jinfeng Li

doi:10.1109/SNAMS.2019.8931720

A Novel Twitter Sentiment Analysis Model with Baseline Correlation for Financial Market Prediction with Improved Efficiency

Xinyi Guo, Jinfeng Li^*

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

58 Citations (Scopus)

Abstract

A novel social networks sentiment analysis model is proposed based on Twitter sentiment score (TSS) for real-time prediction of the future stock market price FTSE 100, as compared with conventional econometric models of investor sentiment based on closed-end fund discount (CEFD). The proposed TSS model features a new baseline correlation approach, which not only exhibits a decent prediction accuracy, but also reduces the computation burden and enables a fast decision making without the knowledge of historical data. Polynomial regression, classification modelling and lexicon-based sentiment analysis are performed using R. The obtained TSS predicts the future stock market trend in advance by 15 time samples (30 working hours) with an accuracy of 67.22% using the proposed baseline criterion without referring to historical TSS or market data. Specifically, TSS's prediction performance of an upward market is found far better than that of a downward market. Under the logistic regression and linear discriminant analysis, the accuracy of TSS in predicting the upward trend of the future market achieves 97.87%

Original language	English
Title of host publication	2019 6th International Conference on Social Networks Analysis, Management and Security, SNAMS 2019
Editors	Mohammad Alsmirat, Yaser Jararweh
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	472-477
Number of pages	6
ISBN (Electronic)	9781728129464
DOIs	https://doi.org/10.1109/SNAMS.2019.8931720
Publication status	Published - Oct 2019
Externally published	Yes
Event	6th International Conference on Social Networks Analysis, Management and Security, SNAMS 2019 - Granada, Spain Duration: 22 Oct 2019 → 25 Oct 2019

Publication series

Name	2019 6th International Conference on Social Networks Analysis, Management and Security, SNAMS 2019

Conference

Conference	6th International Conference on Social Networks Analysis, Management and Security, SNAMS 2019
Country/Territory	Spain
City	Granada
Period	22/10/19 → 25/10/19

Keywords

big data analytics
closed-end fund discounts
financial prediction
lexicon-based classification
Twitter sentiment

Access to Document

10.1109/SNAMS.2019.8931720

Cite this

Guo, X., & Li, J. (2019). A Novel Twitter Sentiment Analysis Model with Baseline Correlation for Financial Market Prediction with Improved Efficiency. In M. Alsmirat, & Y. Jararweh (Eds.), 2019 6th International Conference on Social Networks Analysis, Management and Security, SNAMS 2019 (pp. 472-477). Article 8931720 (2019 6th International Conference on Social Networks Analysis, Management and Security, SNAMS 2019). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/SNAMS.2019.8931720

Guo, Xinyi ; Li, Jinfeng. / A Novel Twitter Sentiment Analysis Model with Baseline Correlation for Financial Market Prediction with Improved Efficiency. 2019 6th International Conference on Social Networks Analysis, Management and Security, SNAMS 2019. editor / Mohammad Alsmirat ; Yaser Jararweh. Institute of Electrical and Electronics Engineers Inc., 2019. pp. 472-477 (2019 6th International Conference on Social Networks Analysis, Management and Security, SNAMS 2019).

@inproceedings{652f9c807c5c4a3689867a2b0e6b5bd4,

title = "A Novel Twitter Sentiment Analysis Model with Baseline Correlation for Financial Market Prediction with Improved Efficiency",

abstract = "A novel social networks sentiment analysis model is proposed based on Twitter sentiment score (TSS) for real-time prediction of the future stock market price FTSE 100, as compared with conventional econometric models of investor sentiment based on closed-end fund discount (CEFD). The proposed TSS model features a new baseline correlation approach, which not only exhibits a decent prediction accuracy, but also reduces the computation burden and enables a fast decision making without the knowledge of historical data. Polynomial regression, classification modelling and lexicon-based sentiment analysis are performed using R. The obtained TSS predicts the future stock market trend in advance by 15 time samples (30 working hours) with an accuracy of 67.22% using the proposed baseline criterion without referring to historical TSS or market data. Specifically, TSS's prediction performance of an upward market is found far better than that of a downward market. Under the logistic regression and linear discriminant analysis, the accuracy of TSS in predicting the upward trend of the future market achieves 97.87%",

keywords = "big data analytics, closed-end fund discounts, financial prediction, lexicon-based classification, Twitter sentiment",

author = "Xinyi Guo and Jinfeng Li",

note = "Publisher Copyright: {\textcopyright} 2019 IEEE.; 6th International Conference on Social Networks Analysis, Management and Security, SNAMS 2019 ; Conference date: 22-10-2019 Through 25-10-2019",

year = "2019",

month = oct,

doi = "10.1109/SNAMS.2019.8931720",

language = "English",

series = "2019 6th International Conference on Social Networks Analysis, Management and Security, SNAMS 2019",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "472--477",

editor = "Mohammad Alsmirat and Yaser Jararweh",

booktitle = "2019 6th International Conference on Social Networks Analysis, Management and Security, SNAMS 2019",

address = "United States",

}

Guo, X & Li, J 2019, A Novel Twitter Sentiment Analysis Model with Baseline Correlation for Financial Market Prediction with Improved Efficiency. in M Alsmirat & Y Jararweh (eds), 2019 6th International Conference on Social Networks Analysis, Management and Security, SNAMS 2019., 8931720, 2019 6th International Conference on Social Networks Analysis, Management and Security, SNAMS 2019, Institute of Electrical and Electronics Engineers Inc., pp. 472-477, 6th International Conference on Social Networks Analysis, Management and Security, SNAMS 2019, Granada, Spain, 22/10/19. https://doi.org/10.1109/SNAMS.2019.8931720

A Novel Twitter Sentiment Analysis Model with Baseline Correlation for Financial Market Prediction with Improved Efficiency. / Guo, Xinyi; Li, Jinfeng.
2019 6th International Conference on Social Networks Analysis, Management and Security, SNAMS 2019. ed. / Mohammad Alsmirat; Yaser Jararweh. Institute of Electrical and Electronics Engineers Inc., 2019. p. 472-477 8931720 (2019 6th International Conference on Social Networks Analysis, Management and Security, SNAMS 2019).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - A Novel Twitter Sentiment Analysis Model with Baseline Correlation for Financial Market Prediction with Improved Efficiency

AU - Guo, Xinyi

AU - Li, Jinfeng

PY - 2019/10

Y1 - 2019/10

N2 - A novel social networks sentiment analysis model is proposed based on Twitter sentiment score (TSS) for real-time prediction of the future stock market price FTSE 100, as compared with conventional econometric models of investor sentiment based on closed-end fund discount (CEFD). The proposed TSS model features a new baseline correlation approach, which not only exhibits a decent prediction accuracy, but also reduces the computation burden and enables a fast decision making without the knowledge of historical data. Polynomial regression, classification modelling and lexicon-based sentiment analysis are performed using R. The obtained TSS predicts the future stock market trend in advance by 15 time samples (30 working hours) with an accuracy of 67.22% using the proposed baseline criterion without referring to historical TSS or market data. Specifically, TSS's prediction performance of an upward market is found far better than that of a downward market. Under the logistic regression and linear discriminant analysis, the accuracy of TSS in predicting the upward trend of the future market achieves 97.87%

AB - A novel social networks sentiment analysis model is proposed based on Twitter sentiment score (TSS) for real-time prediction of the future stock market price FTSE 100, as compared with conventional econometric models of investor sentiment based on closed-end fund discount (CEFD). The proposed TSS model features a new baseline correlation approach, which not only exhibits a decent prediction accuracy, but also reduces the computation burden and enables a fast decision making without the knowledge of historical data. Polynomial regression, classification modelling and lexicon-based sentiment analysis are performed using R. The obtained TSS predicts the future stock market trend in advance by 15 time samples (30 working hours) with an accuracy of 67.22% using the proposed baseline criterion without referring to historical TSS or market data. Specifically, TSS's prediction performance of an upward market is found far better than that of a downward market. Under the logistic regression and linear discriminant analysis, the accuracy of TSS in predicting the upward trend of the future market achieves 97.87%

KW - big data analytics

KW - closed-end fund discounts

KW - financial prediction

KW - lexicon-based classification

KW - Twitter sentiment

UR - http://www.scopus.com/inward/record.url?scp=85077811685&partnerID=8YFLogxK

U2 - 10.1109/SNAMS.2019.8931720

DO - 10.1109/SNAMS.2019.8931720

M3 - Conference contribution

AN - SCOPUS:85077811685

T3 - 2019 6th International Conference on Social Networks Analysis, Management and Security, SNAMS 2019

SP - 472

EP - 477

BT - 2019 6th International Conference on Social Networks Analysis, Management and Security, SNAMS 2019

A2 - Alsmirat, Mohammad

A2 - Jararweh, Yaser

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 6th International Conference on Social Networks Analysis, Management and Security, SNAMS 2019

Y2 - 22 October 2019 through 25 October 2019

ER -

Guo X, Li J. A Novel Twitter Sentiment Analysis Model with Baseline Correlation for Financial Market Prediction with Improved Efficiency. In Alsmirat M, Jararweh Y, editors, 2019 6th International Conference on Social Networks Analysis, Management and Security, SNAMS 2019. Institute of Electrical and Electronics Engineers Inc. 2019. p. 472-477. 8931720. (2019 6th International Conference on Social Networks Analysis, Management and Security, SNAMS 2019). doi: 10.1109/SNAMS.2019.8931720

A Novel Twitter Sentiment Analysis Model with Baseline Correlation for Financial Market Prediction with Improved Efficiency

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this