BERT for stock market sentiment analysis

Research output: Contributions to collected editions/worksArticle in conference proceedingsResearchpeer-review

Authors

  • Matheus Gomes Sousa
  • Kenzo Sakiyama
  • Lucas De Souza Rodrigues
  • Pedro Henrique Moraes
  • Eraldo Fernandes
  • Edson Takashi Matsubara

When breaking news occurs, stock quotes can change abruptly in a matter of seconds. The human analysis of breaking news can take several minutes, and investors in the financial markets need to make quick decisions. Such challenging scenarios require faster ways to support investors. In this work, we propose the use of bidirectional encoder representations from transformers BERT to perform sentiment analysis of news articles and provide relevant information for decision making in the stock market. This model is pre-trained on a large amount of general-domain documents by means of a self-learning task. To fine-tune this powerful model on sentiment analysis for the stock market, we manually labeled stock news articles as positive, neutral or negative. This dataset is freely available and amounts to 582 documents from several financial news sources. We fine-tune a BERT model on this dataset and achieve 72.5% of F-score. Then, we perform some experiments highlighting how the output of the obtained model can provide valuable information to predict the subsequent movements of the Dow Jones Industrial (DJI) Index.

Original languageEnglish
Title of host publicationIEEE 31st International Conference on Tools with Artificial Intelligence : ICTAI 2019 : proceedings : 4-6 November 2019, Portland, Oregon
Number of pages5
Place of PublicationPiscataway
PublisherIEEE - Institute of Electrical and Electronics Engineers Inc.
Publication date11.2019
Pages1589-1593
ISBN (print)978-1-7281-3799-5
ISBN (electronic)978-1-7281-3798-8
DOIs
Publication statusPublished - 11.2019
Externally publishedYes
EventIEEE International Conference on Tools with Artificial Intelligence - Portland, United States
Duration: 04.11.201906.11.2019
Conference number: 13
https://ictai.computer.org/

DOI

Recently viewed

Researchers

  1. Tobias Remschel

Publications

  1. Does sustainable intensification offer a pathway to improved food security for aquatic agricultural system-dependent communities?
  2. Explaining Convergence and Common Trends in the Role of the State in OECD Healthcare Systems
  3. Das Augentierchen
  4. The continued relevance of compromissory clauses as a source of ICJ jurisdiction
  5. A modified epitope identified for generation and monitoring of PSA-specific T cells in patients on early phases of PSA-based immunotherapeutic protocols
  6. Strategizing in NPOs
  7. Diversity and spatio-temporal dynamics of dead wood in a temperate near-natural beech forest (Fagus sylvatica)
  8. Exploring the knowledge landscape of ecosystem services assessments in Mediterranean agroecosystems
  9. Forgetting fire
  10. Patterns of International Organization
  11. Perceptions of Organizational Downsizing
  12. The use of force against terrorists
  13. Welcome home! Introducing SocSES
  14. 'Crawling Jurisdiction'
  15. The importance of interests for understanding retirement
  16. Reprint of: Drivers of within-tree leaf trait variation in a tropical planted forest varying in tree species richness
  17. Towards a Camera-Based Road Damage Assessment and Detection for Autonomous Vehicles
  18. From deforestation to blossom
  19. On the approximation of transport phenomena
  20. Reconsidering adaptation as translation
  21. The politics of expertise and ignorance in the field of migration management
  22. Patterns of organizational (sub)culture and their influence on organizational effectiveness
  23. Chagga women´s connections with nature: fostering relationality through arts-based methods
  24. Resonance measurement of the Lamb shift in hydrogenic sulfur
  25. Assessment Centers
  26. Heat and light
  27. Action, en passant
  28. Einleitung
  29. Sozialwirtschaft
  30. Textkommentierungen
  31. Temporal order judgments