• Digital Humanities and Cultural Heritage
• Publications close
• PL close
• figshare close

Abstract The archaeological site of Ghazali (northern Sudan) provides a rare opportunity to investigate the dynamics of mixed economies and mobility on the fringes on the Nile valley at the time of Christian expansion in Nubia. Thanks to its particular hydrological conditions, Sudan has a long history of diverse groups pursuing different economic activities, with agricultural communities settled along the fertile Nile valley and various mobile pastoralists groups occupying vast areas of the adjacent deserts. Ghazali represents an early medieval Nubian rural site with an extensive funerary zone. Somewhat removed from the Nile valley, Ghazali extends along the western bank of a large wadi, Wadi Abu Dom, running across the Bayuda desert, dated ca. 7th–13th century CE. Multi-isotopic analysis of human tooth enamel from Cemeteries 1, 3, and 4 was used to explore patterns of mobility among these communities. Ten enamel samples were subjected to 87Sr/86Sr analysis, while 24 individuals were studied for their δ18O values. 87Sr/86Sr and δ18O values were very heterogeneous, suggesting that the Ghazali community, as a whole, benefited from a variety of water sources, perhaps including significant contributions from groundwater wells. We suggest that this adds further support for the reconstruction of a mixed practice of agriculture and animal herding in the neighbouring Bayuda desert. These data add to growing evidence for diverse and flexible mixed economies in eastern Africa that provided food security even under the most challenging of conditions.

While large language models have revolutionised computational text analysis methods, the field is still tilted towards English language resources. Even as there are pre-trained models for some "smaller" languages, the coverage is far from universal, and pre-training large language models is an expensive and complicated task. This uneven language coverage limits comparative social research in terms of its geographical and linguistic scope. We propose a solution that sidesteps these issues by leveraging transfer learning and open-source machine translation. We use English as a bridge language between Hungarian and Polish bills and laws to solve a classification task related to the Comparative Agendas Project (CAP) coding scheme. Using the Hungarian corpus as training data for model fine-tuning, we categorise the Polish laws into 20 CAP categories. In doing so, we compare the performance of Transformer-based deep learning models (monolinguals, such as BERT, and multilinguals such as XLM-RoBERTa) and machine learning algorithms (e.g., SVM). Results show that the fine-tuned large language models outperform the traditional supervised learning benchmarks but are themselves surpassed by the machine translation approach. Overall, the proposed solution demonstrates a viable option for applying a transfer learning framework for low-resource languages and achieving state-of-the-art results without requiring expensive pre-training.

This paper is an attempt at evaluating roadside shrines and crosses as significant elements of the cultural heritage of Poland and Europe. Evaluation was carried out in the context of the role these objects play in the rural landscape. We examined roadside shrines and crosses that are a testimony of piety of the local community. Roadside sacral architecture was studied within the area of a representative rural commune in South-Eastern Poland. Point evaluation was used to assess the role of shrines and crosses in three most important aspects: spatial, social-cultural, and natural. We evaluated the artistic and historical values of these objects, their significance in contemporary rural landscape structure, as well as material evidence of piety left at these objects by the local people.

We provide a detailed case study showing how social network analysis allows scholars to detect an event affecting the entire historical network under consideration and identify the responsible actors. We study the middle 13th century in Czech lands, where a rigid political structure of noble families surrounding the monarchs led to the uprising of part of the nobility. Having collected data on approximately 2,400 noblemen from 576 charters, we attempted to uncover social network features pointing to the rebellion and expose the noblemen who joined it. We observed, among other such quantifiable features, assortativity increasing before and resetting to random after the rebellion, a drop in the number of stable connections and subgraph similarity between yearly networks and regional titles (burgraves) rising in centrality above royal court officials in that period. The presented methods can be directly translated to other person-document data of comparable or larger sizes, and we hope it can help detect or disambiguate the timing of similar major events and the roles of people involved in them.

Emotion recognition in real life from physiological signals provided by wrist worn devices still remains a great challenge especially due to difficulties with gathering annotated emotional events. For that purpose, we suggest building pretrained machine learning models capable of detecting intense emotional states. This work aims to explore the cold start problem, where no data from the target subjects (users) are available at the beginning of the experiment to train the reasoning model. To address this issue, we investigate the potential of pergroup personalization and the amount of data needed to perform it. Our results on real-life data indicate that even a week’s worth of personalized data improves the model performance.

This paper presents new excavation data and new radiometric datesfor Jebel Moya, south-central Sudan. These data suggest revisions toprevious chronological understandings of the site. New excavations,initiated in 2017, show a longer, more continuous occupation of thesite than has been previously recognised. Archaeozoological andarchaeobotanical analyses provide evidence for domesticatedtaxa. Archaeobotanical evidence is dominated by domesticatedsorghum (Sorghum bicolor), radiocarbon dated to c. 2550–2210 BC.Faunal remains include cattle and goat/sheep. A late thirdmillenniumBC date on the human skeleton excavated in the 2017season also shows that mortuary activity began early in the site’shistory, contemporary with domesticated faunal and botanicalremains. These initial results indicate the long-term association ofthe site with pastoralism and agriculture and with environmentalchange. Jebel Moya’s continued potential to serve as achronological and cultural reference point for future studies insouth-central Sudan and the eastern Sahel is reinforced.

This paper examines whether the distribution of creative actors (firms and employees) among Dutch urban agglomerations is related to historically shaped culture heritage assets (cultural amenities and historical monuments). The concept of a creative–cultural complex is introduced to explore the synergy between urban amenities with a high cultural heritage value and their magnet function for firms and people. The paper offers a concise overview of the creativity–cultural heritage nexus, provides an operational framing of the research, and describes briefly the relative growth of the creative sector in urban labour market regions in the Netherlands. It addresses the spatial–economic profile of creative actors in four large urban agglomerations (Amsterdam, Rotterdam, The Hague and Utrecht), which have a wealth of cultural assets. The findings show a concentration trend of creative actors in these agglomerations. We then test the general proposition that differences in these spatial concentration patterns are inter alia related to differences in the local presence of cultural amenities and historical monuments in Dutch municipalities, combined with other moderator variables (urban size and agglomeration advantages). We develop a conceptual model and employ a regression analysis to test a correlation between creative actors and historical–cultural amenities at a local level. The paper concludes that local historical–cultural heritage may function as a pull factor that is positively correlated with the local creative economy. This leads to important policy lessons on creative–cultural complexes.