Human-Centred Machine Learning Approaches for Smart Cultural Heritage Spaces: A Multicontinental Review

Abstract

The influence of digital technologies on the Cultural Heritage sector has grown as the use of Artificial Intelligence (AI), the Internet of Things (IOT), Virtual Reality (VR) and Augmented Reality (AR) has become more dominant in society. The digitisation of Cultural Heritage content can be seen across many areas of the world such as in the European Union (EU) within projects like meSch and Emotive that were funded under the Horizon 2020 research and innovation funding programme to support personalisation and education. Machine learning techniques have also been utilised in culturally significant work across Asia and Africa in sectors such as education, healthcare, agriculture, and Cultural Heritage with the goal of improving the life and wellbeing of people in these regions. This paper aims to deduce key machine learning techniques that are applicable for smart Cultural Heritage spaces and determine their adherence with the Human-Centred philosophy in selected projects within Africa, Asia, and Europe. The techniques chosen were Collaborative Filtering and Unsupervised Learning and whilst the results indicated that human-centredness was evident there were areas which could be improved to ensure a broad adherence with this philosophical approach.