Chapter 11 Natural Language Processing: An Application in Finance
Description
With natural language processing methods, analysts now have access to new data from text, for example. It is possible to program an algorithm and synthesize corporate financial reports. It is also possible to have algorithms read industry patents and extract quantitative information from them. This is called unstructured data. In this session, we will use some examples of unstructured data to show their usefulness for issues of interest to international business.
Concepts discussed :
1 natural language process
2 polarity analysis
3 sentiment analysis
4 analysis of institutional dimensions using unstructured data
Pre-Session Activities/Resources
- Warin, Thierry. 2020. “The Speeches of the European Central Bank’s Presidents: An NLP Study.” Global Economy Journal 20 (02): 2050009. https://doi.org/10.1142/S2194565920500098.
Session Activities/Resources
- Warin, Thierry. 2018a. “Connectivity and Closeness Among International Financial Institutions: A Network Theory Perspective.” International Journal of Comparative Management 1 (3): 225-54. https://doi.org/10.1504/IJCM.2018.094479.
Post-Session Activities/Resources
General Resources
Sanger, William, and Thierry Warin. 2019. “Dataset of Jaccard Similarity Indices from 1,597 European Political Manifestos Across 27 Countries (1945-2017).” Data in Brief 24 (June): 103907. https://doi.org/10.1016/j.dib.2019.103907.
From Marcellis-Warin, Nathalie, William Sanger, and Thierry Warin. 2017. “A Network Analysis of Financial Conversations on Twitter.” International Journal of Web Based Communities 13 (3): 281-310.
https://www.theguardian.com/commentisfree/2020/sep/08/robot-wrote-this-article-gpt-3