Using digital archaeology and machine learning to determine sex in finger flutings.

One of the earliest and most enigmatic forms of rock art are finger flutings and previous methods of studying them relied on biometric finger ratios from modern populations to make assumptions about the people who left the flutings, which is theoretically and methodologically problematic. This work is a proof-of-concept for a paradigm shift away from error-prone human measurements and controversial theories to computational digital archaeology methods for an innovative experimental design using a tactile, virtual, and machine learning approach. We propose a digital archaeology experiment using a tactile and virtual approach based on multiple samples from 96 participants. We trained a machine learning model on the known data to determine the sex of the person who made the fluting. While the virtual dataset did not provide sufficiently distinct features for reliable sex classification, the tactile experiment results showed potential for the identification of the sex of fluting artists, but more samples are needed to make any generalization. The significant contribution of this study is the development of a foundational set of methods and materials. We provide a novel digital archaeology approach for data creation, data collection, and analysis that makes the experiment replicable, scalable, and quantifiable.