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.

Measuring a Texts Fairness Dimensions Using Machine Learning Based on Social Psychological Factors

Fairness is a principal social value that can be observed in civilisations around the world. A manifestation of this is in social agreements, often described in texts, such as contracts. Yet, despite the prevalence of such, a fairness metric for texts describing a social act remains wanting. To address this, we take a step back to consider the problem based on first principals. Instead of using rules or templates, we utilise social psychology literature to determine the principal factors that humans use when making a fairness assessment. We then attempt to digitise these using word embeddings into a multi-dimensioned sentence level fairness perceptions vector to serve as an approximation for these fairness perceptions. The method leverages a pro-social bias within word embeddings, for which we obtain an F1= 81.0. A second approach, using PCA and ML based on the said fairness approximation vector produces an F1 score of 86.2. We detail improvements that can be made in the methodology to incorporate the projection of sentence embedding on to a subspace representation of fairness.