Geoparsing history: Locating commodities in ten million pages of nineteenth-century sources

Alex, Beatrice; Clifford, James; Coates, Colin M.; Klein, Ewen; Watson, Andrew

doi:10.1080/01615440.2015.1116419

Cited by 19 publications

(12 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Currently ongoing work is also addressing the application and extension of the methods presented in this article to different problems within the broad field of digital humanities, particularly problems that involve the analysis of toponyms in context (e.g., disambiguating place name references in textual documents (Santos, Anastácio, and Martins 2015;Wing 2016; Ardanuy and Sporleder 2017)). Recent work within the geospatial humanities, particularly within the context of historical geographic information systems, has highlighted the importance of automated methods for handling toponyms (Smith and Crane 2001;Grover et al 2010;Rupp et al 2013;Simon et al 2014;Gregory et al 2015;Murrieta-Flores et al 2015;Blank and Henrich 2016;Wing 2016;Murrieta-Flores, Donaldson, and Gregory 2017;Clifford et al 2016;Butler et al 2017). Approaches looking to map and analyze the geographies mentioned in large collections of historical materials (e.g., historical newspapers, letters, governmental reports, epistolaries, travel guides, tabular itineraries, and many other types of records) are often confronted with the issue of correctly matching alternative forms of place names (e.g., involving spelling variations, historical changes, OCR errors, etc.)…”

Section: Correctly Classifiedmentioning

confidence: 99%

Learning to combine multiple string similarity metrics for effective toponym matching

Santos

Murrieta-Flores

Martins

2017

International Journal of Digital Earth

View full text Add to dashboard Cite

Several tasks related to geographical information retrieval and to the geographical information sciences involve toponym matching, i.e., the problem of matching place names that share a common referent. In this article, we present the results of a wideranging 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 learning, particularly when considering ensembles of decision trees, can achieve good results on this task, significantly outperforming the individual similarity metrics.

show abstract

Section: Correctly Classifiedmentioning

confidence: 99%

Learning to combine multiple string similarity metrics for effective toponym matching

Santos

Murrieta-Flores

Martins

2017

International Journal of Digital Earth

View full text Add to dashboard Cite

show abstract

“…While there has been previous work on bootstrapping and mapping concepts in other types of historical texts (e.g. commodities in historical collections on nineteenth century trade in the British empire [Klein et al, 2014, Hinrichs et al, 2015, Clifford et al, 2016) we are unaware of other work where this is done with respect to narrative document structure across a historical collection.…”

Section: Understanding the Genre Of Outbreak Reportsmentioning

confidence: 99%

Plague Dot Text: Text mining and annotation of outbreak reports of the Third Plague Pandemic (1894-1952)

Casey¹,

Bennett²,

Tobin³

et al. 2021

Journal of Data Mining &Amp; Digital Humanities

Self Cite

View full text Add to dashboard Cite

The design of models that govern diseases in population is commonly built on information and data gathered from past outbreaks. However, epidemic outbreaks are never captured in statistical data alone but are communicated by narratives, supported by empirical observations. Outbreak reports discuss correlations between populations, locations and the disease to infer insights into causes, vectors and potential interventions. The problem with these narratives is usually the lack of consistent structure or strong conventions, which prohibit their formal analysis in larger corpora. Our interdisciplinary research investigates more than 100 reports from the third plague pandemic (1894-1952) evaluating ways of building a corpus to extract and structure this narrative information through text mining and manual annotation. In this paper we discuss the progress of our ongoing exploratory project, how we enhance optical character recognition (OCR) methods to improve text capture, our approach to structure the narratives and identify relevant entities in the reports. The structured corpus is made available via Solr enabling search and analysis across the whole collection for future research dedicated, for example, to the identification of concepts. We show preliminary visualisations of the characteristics of causation and differences with respect to gender as a result of syntactic-category-dependent corpus statistics. Our goal is to develop structured accounts of some of the most significant concepts that were used to understand the epidemiology of the third plague pandemic around the globe. The corpus enables researchers to analyse the reports collectively allowing for deep insights into the global epidemiological consideration of plague in the early twentieth century.

show abstract

“…This is the case of research using NER for materials with disparate qualities of digitization and OCR, non-European or classical languages, or collections featuring spelling variations (Alex et al, 2012;Batjargal et al, 2014;Neudecker et al, 2014;Nagai et al, 2015;Erdmann et al, 2016;Kettunen et al, 2016). Previous research within Digital Humanities has also tackled the related problem of text geoparsing, leveraging NER methods for recognizing place references in text, often together with other heuristics for the complete resolution of place references into gazetteer entries and/or geographical coordinates (Rayson et al, 2006;Baron and Rayson, 2008;Pilz et al, 2008;Grover et al, 2010;Freire et al, 2011;Gregory and Hardie, 2011;Brown et al, 2012;Alex et al, 2015;Gregory et al, 2015;Santos et al, 2015a,b;Wing, 2015;Clifford et al, 2016).…”

Section: Ner In Historical Documentsmentioning

confidence: 99%

Ensemble Named Entity Recognition (NER): Evaluating NER Tools in the Identification of Place Names in Historical Corpora

Won

Murrieta-Flores

Martins

2018

Front. Digit. Humanit.

View full text Add to dashboard Cite

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.

show abstract

Geoparsing history: Locating commodities in ten million pages of nineteenth-century sources

Cited by 19 publications

References 10 publications

Learning to combine multiple string similarity metrics for effective toponym matching

Learning to combine multiple string similarity metrics for effective toponym matching

Plague Dot Text: Text mining and annotation of outbreak reports of the Third Plague Pandemic (1894-1952)

Ensemble Named Entity Recognition (NER): Evaluating NER Tools in the Identification of Place Names in Historical Corpora

Contact Info

Product

Resources

About