Reconstructing Pompeian Households
This addresses the issue of modern cultural assumptions affecting household archaeology in Pompeii, offering an incremental improvement for archaeologists.
The study tackled the problem of reconstructing Pompeian households by applying a data-driven, unsupervised labeling approach to a database of objects, providing a more objective complement to human interpretation that scales to large datasets.
A database of objects discovered in houses in the Roman city of Pompeii provides a unique view of ordinary life in an ancient city. Experts have used this collection to study the structure of Roman households, exploring the distribution and variability of tasks in architectural spaces, but such approaches are necessarily affected by modern cultural assumptions. In this study we present a data-driven approach to household archeology, treating it as an unsupervised labeling problem. This approach scales to large data sets and provides a more objective complement to human interpretation.