Knowledge

Artificial Intelligence, now commonly called AI, is having an increasingly big impact on society. There are fears that may be negatives or downsides, especially when Artificial Intelligence is used unethically. But how are humans guiding these machines to know whether the choice, the decision, is ethical? Since 2007, one way to check the ethicality of any choice has been to apply the JUSTICE model. This framework helps practitioners decide whether a specific action is or is not ethical by looking through one or more of the seven JUSTICE lenses: Justice, Utilitarian, Spiritual Values, TV rule or Transparency, Influence, Core, and Emergency. Now, in this era of increasing prevalence of Artificial Intelligence, with humans making decisions often together with machines, can the JUSTICE framework still be useful? Yes, it can. We look at each of those seven components. Each may give guidance in some situations. Of the seven, it seems that T or the TV test is most likely to give guidance in this new era.

Almost all societal grand challenges, whether concerning the environment, health, well-being, or the development of sustainable economic models, have at their heart a need to understand people’s behaviour. However, uniting data and insights across disparate fields requires an explicit and shared understanding of concepts, variables, and ideas (e.g., how to characterise and differentiate behaviours). Ontologies provide a mechanism for creating this explicit and shared understanding and are starting to be developed and used in the social and behavioural sciences. This paper proposes an online co-design approach to use and develop ontologies of behaviour to specify the characteristics of behaviour (e.g., habitual, changeable, effortless) and studies that investigate behaviour as part of a project designed to understand how behaviours are related. We report on our experience of collaborative co-development of ontologies using real-time interactive tools and reflect on the benefits and challenges of our approach. We also offer a set of recommendations for researchers interested in applying such methods to co-develop ontologies. The work contributes to efforts to understand the characteristics of behaviour and enable these to be used to understand questions about behaviour (e.g., is poor sleep associated with greater engagement in habitual behaviours?).

This article presents a case study showing the development of a chatbot, named Selene, in a Software-as-a-Service platform for behavioral analysis using Retrieval-Augmented Generation (RAG) integrating domain-specific knowledge and enforcing adherence to organizational rules to improve response quality. Selene is designed to provide deep analyses and practical recommendations that help users optimize organizational behavioral development. To ensure that the RAG pipeline had updated information, we implemented an Extract, Transform, and Load process that updated the knowledge base of the pipeline daily and applied prompt engineering to ensure compliance with organizational rules and directives, using GPT-4 as the underlying language model of the chatbot, which was the state-of-the-art model at the time of deployment. We followed the Generative AI Project Life Cycle Frameworkas the basic methodology to develop this system. To evaluate Selene, we used the DeepEval library, showing that it provides appropriate responses and aligning with organizational rules. Our results show that the system achieves high answer relevancy in 78% of the test cases achieved and a complete absence of bias and toxicity issues. This work provides practical insights for organizations deploying similar knowledge-based chatbot systems.