Computational finance is one of the fastest-growing application areas for natural language processing technologies. Already today, algorithmic trading funds are successfully using robo readers and sentiment analysis techniques to support adaptive algorithms that are capable of making automated decisions with little or no human intervention. However, these technologies are still in a nascent state and the competition to improve approaches within the industry is fierce. In this chapter, we discuss financial news analytics and learning strategies that help machines combine domain knowledge with other linguistic information that is extracted from text sources.We provide an overview of existing linguistic resources and methodological approaches that can be readily utilized to develop knowledge-driven solutions for financial news analysis.
CITATION STYLE
Upreti, B. R., Back, P. M., Malo, P., Ahlgren, O., & Sinha, A. (2019). Knowledge-driven approaches for financial news analytics. In Network Theory and Agent-Based Modeling in Economics and Finance (pp. 375–404). Springer Singapore. https://doi.org/10.1007/978-981-13-8319-9_19
Mendeley helps you to discover research relevant for your work.