The spatial humanities constitute a rapidly developing research field that has the potential to create a step-change in the ways in which the humanities deal with geography and geographical information. As yet, however, research in the spatial humanities is only just beginning to deliver the applied contributions to knowledge that will prove its significance. Demonstrating the potential of innovations in technical fields is, almost always, a lengthy process, as it takes time to create the required datasets and to design and implement appropriate techniques for engaging with the information those datasets contain. Beyond this, there is the need to define appropriate research questions and to set parameters for interpreting findings, both of which can involve prolonged discussion and debate. The spatial humanities are still in early phases of this process. Accordingly, the purpose of this special issue is to showcase a set of exemplary studies and research projects that not only demonstrate the field's potential to contribute to knowledge across a range of humanities disciplines, but also to suggest pathways for future research. Our ambition is both to demonstrate how the application of exploratory techniques in the spatial humanities offers new insights about the geographies embedded in a diverse range of texts (including letters, works of literature, and official reports) and, at the same time, to encourage other scholars to integrate these techniques in their research
31 October 2017 in International Journal of Geographical Information Science
Toponym matching, i.e. pairing strings that represent the same real-world location, is a fundamental problemfor several practical applications. The current state-of-the-art relies on string similarity metrics, either specifically developed for matching place names or integrated within methods that combine multiple metrics. However, these methods all rely on common sub-strings in order to establish similarity, and they do not effectively capture the character replacements involved in toponym changes due to transliterations or to changes in language and culture over time. In this article, we present a novel matching approach, leveraging a deep neural network to classify pairs of toponyms as either matching or nonmatching. The proposed network architecture uses recurrent nodes to build representations from the sequences of bytes that correspond to the strings that are to be matched. These representations are then combined and passed to feed-forward nodes, finally leading to a classification decision. We present the results of a wide-ranging evaluation on the performance of the proposed method, using a large dataset collected from the GeoNames gazetteer. These results show that the proposed method can significantly outperform individual similarity metrics from previous studies, as well as previous methods based on supervised machine learning for combining multiple metrics.
The field of Spatial Humanities has advanced substantially in the past years. The identification and extraction of toponyms and spatial information mentioned in historical text collections has allowed its use in innovative ways, making possible the application of spatial analysis and the mapping of these places with geographic information systems. For instance, automated place name identification is possible with Named Entity Recognition (NER) systems. Statistical NER methods based on supervised learning, in particular, are highly successful with modern datasets. However, there are still major challenges to address when dealing with historical corpora. These challenges include language changes over time, spelling variations, transliterations, OCR errors, and sources written in multiple languages among others. In this article, considering a task of place name recognition over two collections of historical correspondence, we report an evaluation of five NER systems and an approach that combines these through a voting system. We found that although individual performance of each NER system was corpus dependent, the ensemble combination was able to achieve consistent measures of precision and recall, outperforming the individual NER systems. In addition, the results showed that these NER systems are not strongly dependent on preprocessing and translation to Modern English.
Investigaciones arqueológicas, históricas y etnográficas han demostrado como los ambientes de montaña tienen una profunda influencia en las dinámicas socioculturales de las comunidades que viven en ellos y en sus áreas vecinas. El desarrollo de estas sociedades tiende a producirse en los márgenes, usualmente lejos de los centros de poder político. Esta marginación se extiende también a la circulación en estas regiones, donde las cordilleras suelen constituir poderosos obstáculos debido a su configuración natural que juega un papel central en sus estrategias, comercio y movimiento humano. Durante la Prehistoria Reciente, la constitución de Sierra Morena Occidental (España) moldeó tanto las vías de tránsito a través de las montañas, como las rutas históricas de comunicación que atraviesan Andalucía. Utilizando una metodología de Sistemas de Información Geográfica diseñada específicamente para identificar características en el paisaje de particular relevancia para el movimiento humano (como corredores naturales, puntos de cruce y áreas naturales de tránsito), se examinó el papel que la accesibilidad del terreno tuvo para las comunidades de esa región durante la Prehistoria Reciente. Mediante este análisis concluimos que la ubicación de sus hábitats y lugares simbólicos se encuentran estrechamente relacionados con corredores naturales, posiblemente debido a una creciente importancia de las actividades de pastoreo.
2 September 2017 in International Journal of Digital Earth
Several tasks related to geographical information retrieval and to the geographical information sciences involve toponym matching, that is, the problem of matching place names that share a common referent. In this article, we present the results of a wide-ranging evaluation on the performance of different string similarity metrics over the toponym matching task. We also report on experiments involving the usage of supervised machine learning for combining multiple similarity metrics, which has the natural advantage of avoiding the manual tuning of similarity thresholds. Experiments with a very large dataset show that the performance differences for the individual similarity metrics are relatively small, and that carefully tuning the similarity threshold is important for achieving good results. The methods based on supervised machine learning, particularly when considering ensembles of decision trees, can achieve good results on this task, significantly outperforming the individual similarity metrics.
High-resolution population grids built from historical census data can ease the analyses of geographical population changes, at the same time also facilitating the combination of population data with other GIS layers to perform analyses on a wide range of topics. This article reports on experiments with a hybrid spatial disaggregation technique that combines the ideas of dasymetric mapping and pycnophylactic interpolation, using modern machine learning methods to combine different types of ancillary variables, in order to disaggregate historical census data into a 200 m resolution grid. We specifically report on experiments related to the disaggregation of historical population counts from three different national censuses which took place around 1900, respectively in Great Britain, Belgium, and the Netherlands. The obtained results indicate that the proposed method is indeed highly accurate, outperforming simpler disaggregation schemes based on mass-preserving areal weighting or pycnophylactic interpolation. The best results were obtained using modern regression methods (i.e., gradient tree boosting or convolutional neural networks, depending on the case study), which previously have only seldom been used for spatial disaggregation.