Classifying Ethics Codes Using Natural Language Processing
Business ethics scholars have varied opinions of corporate ethics codes. Many advocate them as a way to contribute to an organizational environment in which ethics will be a regular consideration in the decision-making process. Critics assert that codes of ethics are mere window dressings written to protect the company from litigation or to comply with regulations. The authors maintain that language is a key to distinguishing between these two properties and an aid to how employees and other stakeholders should view a code’s intent. However, language is often ambiguous to the reader and results of research on ethics codes are often in conflict. This chapter addresses the issue of intent by quantifying the content of ethics codes. Methodologies from natural language processing (NLP) and machine learning are applied in a novel way to classify ethics codes. Codes from companies selected from lists of “Ethical” companies are compared with codes from the Fortune 500 companies. The model’s findings indicate that ethics codes for some of these groups of companies can be distinguishable.
KeywordsEthics codes Codes of conduct Natural language processing Machine learning Corporate social responsibility
The authors wish to thank Adam Meyers of New York University for his invaluable advice on this project.
- Bird, S., Loper, E., & Klein, E. (2009). Natural Language Processing with Python. Beijing: O’Reilly Media Inc.Google Scholar
- Cahn, E. S. (2014). Measures of Corporate Social Business Performance and Ethical Decisions: A Review and Critique. Southern Journal of Business and Ethics, 6, 142–152.Google Scholar
- Farrell, H., & Farrell, B. J. (1998). The Language of Business Codes of Ethics: Implications of Knowledge and Power. Journal of Business Ethics, 17(6), 587.Google Scholar
- McGuire, J. B., Sundgren, A., & Schneeweis, T. (1988). Corporate Social Responsibility and Firm Performance. Academy of Management Journal, 31(4), 854–872.Google Scholar
- Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Prettenhofer, P., Weiss, R., Dubourg, V., Vanderplas, J., Passos, A., Cournapeau, D., Brucher, M., Perrot, M., & Duchesnay, É. (2011). Scikit-Learn: Machine Learning in Python. Journal of Machine Learning Research, 12, 2825–2830.Google Scholar
- Peldszus, A., & Stede, M. (2016). Rhetorical Structure and Argumentation Structure in Monologue Text. ACL, 103.Google Scholar
- Rodrigues, U., & Stegemoller, M. (2010). Placebo Ethics. Virginia Law Review, 96(1), 1–68.Google Scholar
- Russell, S., & Norvig, P. (2002). Artificial Intelligence: A Modern Approach (2nd ed.). Upper Saddle River: Prentice Hall.Google Scholar
- Spencer, B. A., & Taylor, G. S. (1987). A Within and Between Analysis of the Relationship Between Corporate Social Responsibility and Financial Performance. Akron Business and Economic Review, 18(3), 7–18.Google Scholar
- Stede, M. (2016, October 7). Argumentation and Discourse Structure: Some Relationships. NLP Talk Presented at Columbia University.Google Scholar