High-frequency news sentiment and its application to forex market prediction

Research output: Chapter in Book/Report/Conference proceedingPaper in conference proceeding

Standard

High-frequency news sentiment and its application to forex market prediction. / Xing, Frank Z.; Hoang, Duc Hong; Vo, Dinh Vinh.

Proceedings of the 54th Annual Hawaii International Conference on System Sciences, HICSS 2021. ed. / Tung X. Bui. IEEE Computer Society, 2021. p. 1583-1592 (Proceedings of the Annual Hawaii International Conference on System Sciences; Vol. 2020-January).

Research output: Chapter in Book/Report/Conference proceedingPaper in conference proceeding

Harvard

Xing, FZ, Hoang, DH & Vo, DV 2021, High-frequency news sentiment and its application to forex market prediction. in TX Bui (ed.), Proceedings of the 54th Annual Hawaii International Conference on System Sciences, HICSS 2021. Proceedings of the Annual Hawaii International Conference on System Sciences, vol. 2020-January, IEEE Computer Society, pp. 1583-1592, 54th Annual Hawaii International Conference on System Sciences, HICSS 2021, Virtual, Online, 2021/01/04.

APA

Xing, F. Z., Hoang, D. H., & Vo, D. V. (2021). High-frequency news sentiment and its application to forex market prediction. In T. X. Bui (Ed.), Proceedings of the 54th Annual Hawaii International Conference on System Sciences, HICSS 2021 (pp. 1583-1592). (Proceedings of the Annual Hawaii International Conference on System Sciences; Vol. 2020-January). IEEE Computer Society.

CBE

Xing FZ, Hoang DH, Vo DV. 2021. High-frequency news sentiment and its application to forex market prediction. Bui TX, editor. In Proceedings of the 54th Annual Hawaii International Conference on System Sciences, HICSS 2021. IEEE Computer Society. pp. 1583-1592. (Proceedings of the Annual Hawaii International Conference on System Sciences).

MLA

Xing, Frank Z., Duc Hong Hoang and Dinh Vinh Vo "High-frequency news sentiment and its application to forex market prediction". Bui, Tung X. (ed.). Proceedings of the 54th Annual Hawaii International Conference on System Sciences, HICSS 2021. Proceedings of the Annual Hawaii International Conference on System Sciences. IEEE Computer Society. 2021, 1583-1592.

Vancouver

Xing FZ, Hoang DH, Vo DV. High-frequency news sentiment and its application to forex market prediction. In Bui TX, editor, Proceedings of the 54th Annual Hawaii International Conference on System Sciences, HICSS 2021. IEEE Computer Society. 2021. p. 1583-1592. (Proceedings of the Annual Hawaii International Conference on System Sciences).

Author

Xing, Frank Z. ; Hoang, Duc Hong ; Vo, Dinh Vinh. / High-frequency news sentiment and its application to forex market prediction. Proceedings of the 54th Annual Hawaii International Conference on System Sciences, HICSS 2021. editor / Tung X. Bui. IEEE Computer Society, 2021. pp. 1583-1592 (Proceedings of the Annual Hawaii International Conference on System Sciences).

RIS

TY - GEN

T1 - High-frequency news sentiment and its application to forex market prediction

AU - Xing, Frank Z.

AU - Hoang, Duc Hong

AU - Vo, Dinh Vinh

PY - 2021

Y1 - 2021

N2 - Financial news has been identified as an important alternative information source for modeling market dynamics in recent years. While most of the attention goes to stock markets, the foreign exchange (Forex) market, in contrast, is much less studied. Most of the existing text mining research for the Forex market combine news sentiment with other text features, making the contribution of each factor unclear. To this end, we want to study the role of news sentiment exclusively. In particular, we propose a FinBERT-based model to extract high-frequency news sentiment as a 4-dimensional time series. We examine the efficacy of this news sentiment for Forex market prediction without involving any other semantic feature. Experiments show that our model outperforms alternative sentiment analysis approaches and confirm that news sentiment alone may have predictive power for Forex price movements. The sentiment analysis method seems to have a big potential to improve despite that the current predictive power is still weak. The results deepen our understanding of financial text processing systems.

AB - Financial news has been identified as an important alternative information source for modeling market dynamics in recent years. While most of the attention goes to stock markets, the foreign exchange (Forex) market, in contrast, is much less studied. Most of the existing text mining research for the Forex market combine news sentiment with other text features, making the contribution of each factor unclear. To this end, we want to study the role of news sentiment exclusively. In particular, we propose a FinBERT-based model to extract high-frequency news sentiment as a 4-dimensional time series. We examine the efficacy of this news sentiment for Forex market prediction without involving any other semantic feature. Experiments show that our model outperforms alternative sentiment analysis approaches and confirm that news sentiment alone may have predictive power for Forex price movements. The sentiment analysis method seems to have a big potential to improve despite that the current predictive power is still weak. The results deepen our understanding of financial text processing systems.

M3 - Paper in conference proceeding

AN - SCOPUS:85108373543

T3 - Proceedings of the Annual Hawaii International Conference on System Sciences

SP - 1583

EP - 1592

BT - Proceedings of the 54th Annual Hawaii International Conference on System Sciences, HICSS 2021

A2 - Bui, Tung X.

PB - IEEE Computer Society

T2 - 54th Annual Hawaii International Conference on System Sciences, HICSS 2021

Y2 - 4 January 2021 through 8 January 2021

ER -