Measuring Ethical Values with AI for Better Teamwork

Abstract

Do employees with high ethical and moral values perform better? Comparing personality characteristics, moral values, and risk-taking behavior with individual and team performance has long been researched. Until now, these determinants of individual personality have been measured through surveys. However, individuals are notoriously bad at self-assessment. Combining machine learning (ML) with social network analysis (SNA) and natural language processing (NLP), this research draws on email conversations to predict the personal values of individuals. These values are then compared with the individual and team performance of employees. This prediction builds on a two-layered ML model. Building on features of social network structure, network dynamics, and network content derived from email conversations, we predict personality characteristics, moral values, and the risk-taking behavior of employees. In turn, we use these values to predict individual and team performance. Our results indicate that more conscientious and less extroverted team members increase the performance of their teams. Willingness to take social risks decreases the performance of innovation teams in a healthcare environment. Similarly, a focus on values such as power and self-enhancement increases the team performance of a global services provider. In sum, the contributions of this paper are twofold: it first introduces a novel approach to measuring personal values based on “honest signals” in emails. Second, these values are then used to build better teams by identifying ideal personality characteristics for a chosen task.

Introduction - Social computing: panacea or abyss?

“…However, what social computing can do is use AI to measure ethical and moral values. AI models can measure one's ethical values based on body signals tracked with a smartwatch, based on the words that one uses, and even based on the "honest signals" computed from the email interaction network and dynamics -without even looking at the words that are used (Gloor et al, 2022;Altuntas et al, 2022). This approach will enable you to know your personal moral and ethical values, as well as the ones of the people interacting with you.…”

“…For example, the text of emails can be used to infer personality traits such as OCEAN (Openness, Conscientiousness, Extroversion, Agreeability, Neuroticism) of the authors. The same AI algorithms (Gloor et al, 2022) also detect moral and ethical core values and risk behaviors of individuals (Altuntas et al, 2022). These email analytics can also detect team communication patterns, and improve team communication and collaboration by mirroring these patterns back by "virtual mirroring".…”

Assessment of Personal Values for Data-Driven Human Resource Management

“…Rather than directly measuring personal values, Altuntas, Gloor, and Budner (2022) developed a machine learning model to predict personal values based on a concept called the Honest Signal (Pentland 2008)-small signs represented by an individual's body movement, short words, or manner of speaking that give away their true intent, personality, emotions, or personal values. Altuntas et al used archived email data to train a model to predict personal values operationalized by Schwartz's theory.…”

Values, Ethics, Morals? On the Use of Moral Concepts in NLP Research

“…Out of the 92 works, more than one quarter (24) deal with predicting moral values from text (e.g., Pavan et al, 2023;Gloor et al, 2022) and 14 papers deal with classification more broadly (e.g., 'ethics classification' (Mainali et al, 2020), classification of ethical arguments according to the three ethical families, and 'moral sentiment' and 'moral stance' classification (e.g., Mooijman et al, 2018;Garten et al, 2016;Botzer et al, 2022)), and thus fall under the umbrella of descriptive ethics. Another 14 papers focus primarily on the production of 'moral data sets', either based on MFT (e.g., Matsuo et al, et al, 2022;Dehghani et al, 2008;Mainali et al, 2020;Jiang et al, 2021b).…”

“…Most of these papers are based on Moral Foundation Theory, with a few exceptions (see § 4). (van den Broek-Altenburg et al, 2021;Altuntas et al, 2022;Rezapour et al, 2019b;van Luenen, 2020;Rezapour et al, 2019a;Vecerdea, 2021;Lan and Paraboni, 2022;Asprino et al, 2022; Constantinescu, 2021;Arsene, 2021;Dondera, 2021;Huang et al, 2022;Liscio et al, 2022;Pavan et al, 2023;Mokhberian et al, 2020;Teernstra et al, 2016;Johnson and Goldwasser, 2019;Maheshwari et al, 2017;Gloor et al, 2022; Alfano et al, 2018;Dahlmeier, 2014;Kiesel et al, 2022;Johnson and Goldwasser, 2018)…”