Spatial analysis of linguistic data with GIS functions

Lee, Jay; Kretzschmar, William A.

doi:10.1080/02693799308901981

Cited by 31 publications

(18 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although basic global spatial autocorrelation statistics were introduced to regional dialectology in Lee and Kretzschmar (1993) and Kretzschmar (1996), measures of spatial autocorrelation have not been used in regional dialectology since, despite their obvious application and their frequent use in other fields. Global Moran's I (Moran, 1948;Odland, 1988) was used to test each linguistic variable for significant levels of positive global spatial autocorrelation to determine if each variable exhibits an overall pattern of regional clustering.…”

Section: Spatial Autocorrelation Analysismentioning

confidence: 99%

A statistical method for the identification and aggregation of regional linguistic variation

2011

View full text Add to dashboard Cite

A B S T R A C T This paper introduces a method for the analysis of regional linguistic variation. The method identifies individual and common patterns of spatial clustering in a set of linguistic variables measured over a set of locations based on a combination of three statistical techniques: spatial autocorrelation, factor analysis, and cluster analysis. To demonstrate how to apply this method, it is used to analyze regional variation in the values of 40 continuously measured, high-frequency lexical alternation variables in a 26-million-word corpus of letters to the editor representing 206 cities from across the United States.

show abstract

Section: Spatial Autocorrelation Analysismentioning

confidence: 99%

A statistical method for the identification and aggregation of regional linguistic variation

2011

View full text Add to dashboard Cite

show abstract

“…This section describes prior work on global methods for quantifying the degree of spatial dependence in a geotagged corpus. 1 While other global spatial statistics exist, we focus on the following three methods because they have been used in previous work on dialect analysis: Moran's I (Grieve, Speelman, and Geeraerts 2011), join count analysis (Lee and Kretzschmar Jr 1993) and the Mantel test (Scherrer 2012). We define a consistent notation across methods.…”

Section: Prior Workmentioning

confidence: 99%

“…Note the similarity to the numerator of Moran's I, which can be written as R W R. The number of agreements can be compared with its expectation under the null hypothesis, yielding a hypothesis test for global autocorrelation (Cliff and Ord 1981). Join count analysis has been applied to the study of dialect by Lee and Kretzschmar Jr (1993), who take each linguistic observation x i ∈ {0, 1} to be a binary variable indicating the presence or absence of a dialect feature. They then build a binary spatial weighting matrix by performing a Delaunay triangulation over the geolocations of participants in dialect interviews, with w ij = 1 if the edge (i, j) appears in the Delaunay triangulation.…”

Section: Join Count Analysismentioning

confidence: 99%

“…The use of statistical methods to analyze spatial dependence has been only lightly studied in sociolinguistics and dialectology. Existing approaches employ classical statistics such as Moran's I (e.g., Grieve, Speelman, and Geeraerts (2011)), join count analysis (e.g., Lee and Kretzschmar Jr (1993)) and the Mantel Test (e.g., Scherrer (2012)); we review these statistics in section 2. These classical approaches suffer from a common problem: each type of test can capture only a specific parametric form of spatial linguistic variation.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Kernel Independence Test for Geographical Language Variation

Nguyen

Eisenstein

2017

Computational Linguistics

View full text Add to dashboard Cite

Quantifying the degree of spatial dependence for linguistic variables is a key task for analyzing dialectal variation. However, existing approaches have important drawbacks. First, they are based on parametric models of dependence, which limits their power in cases where the underlying parametric assumptions are violated. Second, they are not applicable to all types of linguistic data: some approaches apply only to frequencies, others to boolean indicators of whether a linguistic variable is present. We present a new method for measuring geographical language variation, which solves both of these problems. Our approach builds on Reproducing Kernel Hilbert space (RKHS) representations for nonparametric statistics, and takes the form of a test statistic that is computed from pairs of individual geotagged observations without aggregation into predefined geographical bins. We compare this test with prior work using synthetic data as well as a diverse set of real datasets: a corpus of Dutch tweets, a Dutch syntactic atlas, and a dataset of letters to the editor in North American newspapers. Our proposed test is shown to support robust inferences across a broad range of scenarios and types of data.

show abstract

“…To this end, it is necessary to quantify the spatial patterns that are expected to be of relevance. Lee and Kretzschmar (1993) have proposed measuring the 'spatial clustering' of variants. Then, 'Combinations of words may be put together either by experiments or by prior understanding of relations among words.…”

mentioning

confidence: 99%

Lexical meaning and spatial distribution. Evidence from geostatistical dialectometry

Pickl

2013

Literary and Linguistic Computing

View full text Add to dashboard Cite

In the German dialectological literature of the last century, there are several recurring ideas concerning the relation between the meaning of a lexical variable (i.e. a semantic concept) 1 and the way in which its variants (i.e. a concept's designations) are distributed in space. They are mainly based on observations of regularities in the corpora of maps the authors in question had at hand, and can be seen as attempts to systematize the vast amount of seemingly unstructured lexical distributions. However, the accounts that they give are somewhat fragmentary, as they are mostly based on individual observations that lack the support of hard quantitative evidence, and the explanations provided are, on the whole, not very methodical. 2 The main themes that can be distinguished in the relevant literature are the following: • Concepts belonging to the fields of agriculture, crafts or household tend to have a richly varied terminology with variants that are clearly distributed in space. The reason that is given for this is mainly cultural: Purportedly, in these domains cultural practices are spatially limited and the readiness to ado pt cultural influences varies from region to region, which readily leads to the formation of distinct variant areas.

show abstract

Spatial analysis of linguistic data with GIS functions

Cited by 31 publications

References 7 publications

A statistical method for the identification and aggregation of regional linguistic variation

A statistical method for the identification and aggregation of regional linguistic variation

A Kernel Independence Test for Geographical Language Variation

Lexical meaning and spatial distribution. Evidence from geostatistical dialectometry

Contact Info

Product

Resources

About