Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

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

Xing, Frank Z. ; Hoang, Duc Hong LU and Vo, Dinh Vinh LU (2021) 54th Annual Hawaii International Conference on System Sciences, HICSS 2021 In Proceedings of the Annual Hawaii International Conference on System Sciences 2020-January. p.1583-1592
Abstract

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... (More)

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.

(Less)
Please use this url to cite or link to this publication:
author
; and
organization
publishing date
type
Chapter in Book/Report/Conference proceeding
publication status
published
subject
host publication
Proceedings of the 54th Annual Hawaii International Conference on System Sciences, HICSS 2021
series title
Proceedings of the Annual Hawaii International Conference on System Sciences
editor
Bui, Tung X.
volume
2020-January
pages
10 pages
publisher
IEEE Computer Society
conference name
54th Annual Hawaii International Conference on System Sciences, HICSS 2021
conference location
Virtual, Online
conference dates
2021-01-04 - 2021-01-08
external identifiers
  • scopus:85108373543
ISSN
1530-1605
ISBN
9780998133140
language
English
LU publication?
yes
id
4aa48add-4b26-4788-9256-3e6af0d5cf00
date added to LUP
2021-07-16 12:00:52
date last changed
2022-04-27 02:52:59
@inproceedings{4aa48add-4b26-4788-9256-3e6af0d5cf00,
  abstract     = {{<p>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.</p>}},
  author       = {{Xing, Frank Z. and Hoang, Duc Hong and Vo, Dinh Vinh}},
  booktitle    = {{Proceedings of the 54th Annual Hawaii International Conference on System Sciences, HICSS 2021}},
  editor       = {{Bui, Tung X.}},
  isbn         = {{9780998133140}},
  issn         = {{1530-1605}},
  language     = {{eng}},
  pages        = {{1583--1592}},
  publisher    = {{IEEE Computer Society}},
  series       = {{Proceedings of the Annual Hawaii International Conference on System Sciences}},
  title        = {{High-frequency news sentiment and its application to forex market prediction}},
  volume       = {{2020-January}},
  year         = {{2021}},
}