The paper by Brown & Lewis [1] presents an approach to measure seasonal mobility and subsistence practices. In order to do so, the paper proposes a Bayesian mixture model to estimate the annual distribution of shellfish harvesting activity. Following the recommendations of the two reviewers, the paper presents a clear and innovative method to assess seasonal mobility for prehistoric groups, although it could benefit from additional references regarding isotopic literature.

While the adequacy of isotope analysis for estimating mobility patterns in Archaeology has been extensively proven by now, work on specific seasonal mobility is not that much abundant. However, this is a key issue, since seasonal mobility is one of the main social components defining the differences between groups both considering farming vs hunting and gathering or even among hunter-gatherer groups themselves. In this regard, the paper brings a valuable methodological resources that can be used for further research in this issue.

One of its greatest values is the fact that it can quantify the uncertainty present in previous isotope studies in seasonal mobility. As stated by the authors, the model can still undergo several optimisation aspects, but as it stands, it is already providing a valuable asset regarding the quantification of uncertainy in the isotopic studies of seasonal mobility.

Reference

[1] Brown, J. and Lewis, G. (2024). Inferring shellfishing seasonality from the isotopic composition of biogenic carbonate: A Bayesian approach. Zenodo, 7949547, ver. 3 peer-reviewed and recommended by Peer Community in Archaeology. https://doi.org/10.5281/zenodo.7949547

The production of texts in archaeology is vast and multiple in nature, and the archaeologist often misses the true extent of its scope. Machine learning and deep learning have a top place to play in these analyses (Bellat et al 2025), with text extraction methods being therefore a useful tool for reducing complexity and, more specifically, for uncovering elements that may be lost in the midst of so much literary production. This is what Van den Dikkenberg and Brandsen set out to do in the specific case of Vlaardingen Culture (3400-2500 BCE). By using NER (Named Entity Recognition) with BERT (Bidirectional Encoder Representations from Transformers) they were able to recover data related to the location of sites, the relevance of the data and, just as importantly, potential errors and failures in interpretation (Van den Dikkenberg and Brandsen 2025). The contextual aspect is emphasized here by the authors, and is one of the main reasons why BERT is used, which is logically a wake-up call for the future: it is not enough to classify or represent data, it is essential to understand what surrounds it, its contexts and its particularities (Brandsen et al 2022). 

For this, refinement is always advocated, as these models need constant attention in terms of both training data and parameters. This constant search means that this article is not simply an analysis, but that it can be a relevant contribution both to the culture in question and to the way in which we approach and extract relevant information about the grey literature that archaeology produces. Thus, Van den Dikkenberg and Brandsen present us with an article that is eminently practical but which considers the theoretical implications of this automation of the search for the contexts of archaeological data, which reinforces its relevance and, consequently, its recommendation.

References

Bellat, M., Orellana Figueroa, J. D., Reeves, J. S., Taghizadeh-Mehrjardi, R., Tennie, C. & Scholten, T. (2025). Machine learning applications in archaeological practices: A review. https://doi.org/10.48550/arXiv.2501.03840

Brandsen, A., Verberne, S., Lambers, K. & Wansleeben, M. (2022). Can BERT dig it? Named entity recognition for information retrieval in the archaeology domain. Journal on Computing and Cultural Heritage, 15(3), 1–18. https://doi.org/10.1145/3497842

Van den Dikkenberg, L. & Brandsen, A. (2025). Using Text Mining to Search for Neolithic Vlaardingen Culture Sites in the Rhine-Meuse-Scheldt Delta. Zenodo. v2 peer-reviewed and recommended by Peer Community In Archaeology https://doi.org/10.5281/zenodo.14763691

This paper [1] presents an innovative approach to address the prevalent challenge of unbalanced datasets in coin type recognition, shifting the focus from coin class type recognition to coin mint recognition. Despite this shift, the issue of unbalanced data persists. To mitigate this, the authors introduce a method to split larger classes into smaller ones, integrating them into an 'additional class layer'.

Three distinct machine learning (ML) methodologies were employed to identify new possible classes, with one approach utilising unsupervised clustering alongside manual intervention, while the others leverage object detection, and Natural Language Processing (NLP) techniques. However, despite these efforts, overfitting remained a persistent issue, prompting the authors to explore alternative methods such as dataset improvement and Generative Adversarial Networks (GANs).

The paper contributes significantly to the intersection of ML techniques and archaeology, particularly in addressing overfitting challenges. Furthermore, the authors' candid acknowledgment of the limitations of their approaches serves as a valuable resource for researchers encountering similar obstacles.

This study stems from the D4N4 project, aimed at developing a machine learning-based coin recognition model for the extensive "Corpus Nummorum" dataset, comprising over 19,600 coin types and 49,000 coins from various ancient landscapes. Despite encountering challenges with overfitting due to the dataset's imbalance, the authors' exploration of multiple methodologies and transparent documentation of their limitations enriches the academic discourse and provides a foundation for future research in this field.

Reference

[1] Gampe, S. and Tolle, K. (2024). Creating an Additional Class Layer with Machine Learning to counter Overfitting in an Unbalanced Ancient Coin Dataset. Zenodo, 8298077, ver. 4 peer-reviewed and recommended by Peer Community in Archaeology. https://doi.org/10.5281/zenodo.8298077