The Golden Rule as a Heuristic to Measure the Fairness of Texts Using Machine Learning

To treat others as one would wish to be treated is a common formulation of the golden rule (GR). Yet, despite its prevalence as an axiom throughout history, no transfer of this moral philosophy into computational systems exists. In this paper we consider how to algorithmically operationalise this rule so that it may be used to measure sentences such as the boy harmed the girl, and categorise them as fair or unfair. For the purposes of the paper, we define a fair act as one that one would be accepting of if it were done to oneself. A review and reply to criticisms of the GR is made. We share the code for the digitisation of the GR, and test it with a list of sentences. Implementing it within two language models, the USE, and ALBERT, we find F1 scores of 78.0, 85.0, respectively. A suggestion of how the technology may be implemented to avoid unfair biases in word embeddings is made - given that individuals would typically not wish to be on the receiving end of an unfair act, such as racism, irrespective of whether the corpus being used deems such discrimination as praiseworthy.