A Recommender System for Equitable Public Art Curation and Installation

The placement of art in public spaces can have a significant impact on who feels a sense of belonging. In cities, public art communicates whose interests and culture are being favored. In this paper, we propose a graph matching approach with local constraints to build a curatorial tool for selecting public art in a way that supports inclusive spaces. We develop a cost matrix by drawing on Schelling’s model of segregation. Using the cost matrix as an input, the optimization problem is solved via projected gradient descent to obtain a soft assignment matrix. We discuss regularization terms to set curatorial constraints. Our optimization program allocates artwork to public spaces and walls in a way that de-prioritizes “in-group” preferences, by satisfying minimum representation and exposure criteria. We draw on existing literature to develop a fairness metric for our algorithmic output. Using Tufts University as a testbed, we assess the effectiveness of our approach and discuss its potential pitfalls from both a curatorial and equity standpoint.