Automated Ethical Requirements Classification in AI: The ERC4AI Tool

Context: The operationalization of AI ethical principles during the requirements engineering phase is paramount for creating ethically aligned AI systems. However, ethical requirements classification remains a significant challenge due to the abstract nature of ethical principles and the lack of practical tools to support developers. Objective: We introduce the EthicalRequirements4AI, a dataset comprising 1,093 annotated requirements, including ethical and non-ethical requirements. We also provide the Ethical Requirements Classification for AI (ERC4AI), a model for classifying requirements based on AI ethical principles. Method: Passenger Flow and PROMISE datasets were used to construct the EthicalRequirements4AI dataset, encompassing 156 requirements aligned with 11 AI ethical principles and 937 non-ethical requirements. Three language models – XLM-RoBERTa, BERT, and DistilBERT – were evaluated for binary and multi-label classification tasks. Results: BERT achieved the best performance, with a weighted average F1 score of 95\% in binary and 88\% in multi-label classification. The ERC4AI multi-label can classify requirements into Transparency (78\%), Responsibility (81\%), Trust (56\%), and Privacy (65\%), according to F1 score. Conclusions: ERC4AI offers a novel tool for researchers and developers to address ethical concerns early in AI development. The dataset and models are publicly available to foster further research and advancements in practical AI ethics.