Measuring ethical behavior with AI and natural language processing to assess business success

Abstract

Everybody claims to be ethical. However, there is a huge difference between declaring ethical behavior and living up to high ethical standards. In this paper, we demonstrate that “hidden honest signals” in the language and the use of “small words” can show true moral values and behavior of individuals and organizations and that this ethical behavior is correlated to real-world success; however not always in the direction we might expect. Leveraging the latest advances of AI in natural language processing (NLP), we construct three different “tribes” of ethical, moral, and non-ethical people, based on Twitter feeds of people of known high and low ethics and morals: fair and modest collaborators codified as ethical “bees”; hard-working competitive workers as moral “ants”; and selfish, arrogant people as non-ethical “leeches”. Results from three studies involving a total of 49 workgroups and 281 individuals within three different industries (healthcare, business consulting, and higher education) confirm the validity of our model. Associating membership in ethical or unethical tribes with performance, we find that being ethical correlates positively or negatively with success depending on the context.