Authors/Project Team:
Christopher Donaldson – Lancaster University
Ian N. Gregory – Lancaster University
Joanna E. Taylor – University of Manchester

The corpus contains 80 manually digitized texts totaling over 1.5-million word tokens.

Natural language processing (NLP) techniques were used to identify place names and assign these names geographic coordinates—a method called “geoparsing.” But the project members also went beyond what was possible at the time with out-of-the-box NLP libraries and geoparser tools in order to deeply annotate the texts, linking place-name variants and differentiating a wide range of topographical features. As such, the corpus “forms a challenging testbed for geographical text analysis methods” (Rayson et al.).

What you’d need to know to conduct “geographical text analysis”:

Step 1: Geoparsing

If your corpus is not already annotated, you will need to “geoparse”—convert place-names into geographic identifiers.

Geoparsing involves two stages of NLP:

• Named Entity Recognition (NER) – a method for automatically extracting placenames from text data
• Named Entity Disambiguation (NED) – a method for linking the extracted and identified terms with existing knowledge, enabling cross-referencing and connections to metadata such as geo-spatial information.

Tools:

Step 2: Collocation analysis.

The authors go about identifying the specific geographies associated with “beautiful,” “picturesque,” “sublime,” and “majestic” by noting when those terms appear alongside placenames. Thus, the authors develop a dataset of placename co-occurrences or “PNCs” extracted from their corpus. They then assess the frequency of co-occurrence to determine the statistical significance of the association between a given place and one of the aesthetic terms.

Tools:

• NLTK.Collocations: https://www.nltk.org/howto/collocations.html

Step 3: Spatial analysis

With the statistically significant PNCs identified, the authors use geoparsing tools to assign latitude/longitude (mappable) coordinates to each PNC. This enables researchers to analyse the spatial distribution of PNCs through GIS software such as ArcGIS, creating standard dot maps as well as density-smoothed maps. They also use Kulldorf’s Spatial Scan Statistic (traditionally an epidemiological statistic) to identify clusters.

With sophisticated GIS, they can map the spatial coordinates of the PNCs onto topographical and geological datasets, enabling a rich understanding of how places described as “majestic,” for example, map onto different elevations or different geological formations.

Digital terrain models (DTMs) or Digital Elevation Models (DEM) are vector and raster maps that can be imported into GIS tools if they are not already included. National geological surveys provide geology data in the form of GIS line and polygons that can be matched with PNC spatial metadata.

Tools:

• ArcGIS: https://www.arcgis.com/index.html
• QGIS: https://www.qgis.org/en/site/
• SaTScan: https://www.satscan.org/
• Natural Earth: https://www.naturalearthdata.com/downloads/
• pyscan: https://mmath.dev/pyscan/
• BGS Geology 625K: https://www.bgs.ac.uk/datasets/bgs-geology-625k-digmapgb/

Results

Donaldson et al.’s geographic analysis yields some striking findings on how the four aesthetic terms are applied to the Lake District landscape, which the authors summarize thusly:

As we have seen, whereas beautiful and, more especially, picturesque are often associated with geographical features set within, and framed by, their environment, majestic is more typically associated with features that rise above or extend beyond their surroundings. Sublime, true to Burke’s influential conception of the term, stands apart from these other terms in being associated with formations that are massed together in ways that make them difficult to differentiate […] The distinctive geographies associated with the terms beautiful and picturesque, on the one hand, and majestic and sublime, on the other, confirm that the authors of the works in our corpus were, as a whole, relatively discerning about the ways they used aesthetic terminology.

(Donaldson et al. 59)

References Cited: