Conference proceeding
Natural Language Processing for Company Financial Communication Style
2020 Systems and Information Engineering Design Symposium (SIEDS), pp 1-6
Apr 2020
Abstract
Nowadays, financial firms can interpret press releases within few seconds using natural language processing algorithms. Therefore, it is important for public companies to structure its communications in a way that accounts for how the market digests its public information and avoid unnecessary volatility. Companies want to know the impression of their communications, such as investors calls and annual reports, among the investment community including analysts, financial press, and institutional investors. While there have been research papers connecting sentiment analysis of company communication materials to stock movement, research on identifying any similarities in communication styles among public companies has not been a major topic. We aimed to quantify the sentiment of those communication materials and determine if there are any discernible communication styles among leading technology companies. In addition, we conducted analyses and comparisons to stock indices to connect company communication style to market reactions from investors. Our results indicate that there is a signal between sentiment scores derived from Loughran McDonald dictionary and market-residualized stock performance of our company set, highlighting the benefits one can obtain from using NLP techniques.
Metrics
5 Record Views
Details
- Title
- Natural Language Processing for Company Financial Communication Style
- Creators
- Ruslan Askerov - University of AmsterdamEric Kwon - University of AmsterdamLe Michael Song - University of AmsterdamDylan Weber - University of AmsterdamOliver Schaer - University of VirginiaFaraz Dadgostari - Engineering SystemsStephen Adams - University of Amsterdam
- Publication Details
- 2020 Systems and Information Engineering Design Symposium (SIEDS), pp 1-6
- Publisher
- IEEE
- Resource Type
- Conference proceeding
- Language
- English
- Academic Unit
- Decision Sciences (and Management Information Systems)
- Scopus ID
- 2-s2.0-85087086870
- Other Identifier
- 991021862309604721