Uncorrelated Geo-Text Inhibition Method Based on Voronoi K-Order and Spatial Correlations in Web Maps

Unstructured geo-text annotations volunteered by users of web map services enrich the basic geographic data. However, irrelevant geo-texts can be added to the web map, and these geo-texts reduce utility to users. Therefore, this study proposes a method to detect uncorrelated geo-text annotations bas...

Full description

Bibliographic Details
Main Authors: Yufeng He, Yehua Sheng, Yunqing Jing, Yue Yin, Ahmad Hasnain
Format: Article
Language:English
Published: MDPI AG 2020-06-01
Series:ISPRS International Journal of Geo-Information
Subjects:
Online Access:https://www.mdpi.com/2220-9964/9/6/381
_version_ 1797565732443127808
author Yufeng He
Yehua Sheng
Yunqing Jing
Yue Yin
Ahmad Hasnain
author_facet Yufeng He
Yehua Sheng
Yunqing Jing
Yue Yin
Ahmad Hasnain
author_sort Yufeng He
collection DOAJ
description Unstructured geo-text annotations volunteered by users of web map services enrich the basic geographic data. However, irrelevant geo-texts can be added to the web map, and these geo-texts reduce utility to users. Therefore, this study proposes a method to detect uncorrelated geo-text annotations based on Voronoi k-order neighborhood partition and auto-correlation statistical models. On the basis of the geo-text classification and semantic vector transformation, a quantitative description method for spatial autocorrelation was established by the Voronoi weighting method of inverse vicinity distance. The Voronoi k-order neighborhood self-growth strategy was used to detect the minimum convergence neighborhood for spatial autocorrelation. The Pearson method was used to calculate the correlation degree of the geo-text in the convergence region and then deduce the type of geo-text to be filtered. Experimental results showed that for given geo-text types in the study region, the proposed method effectively calculated the correlation between new geo-texts and the convergence region, providing an effective suggestion for preventing uncorrelated geo-text from uploading to the web map environment.
first_indexed 2024-03-10T19:17:11Z
format Article
id doaj.art-adb921b9f18c47248584a15cda0bcb99
institution Directory Open Access Journal
issn 2220-9964
language English
last_indexed 2024-03-10T19:17:11Z
publishDate 2020-06-01
publisher MDPI AG
record_format Article
series ISPRS International Journal of Geo-Information
spelling doaj.art-adb921b9f18c47248584a15cda0bcb992023-11-20T03:20:22ZengMDPI AGISPRS International Journal of Geo-Information2220-99642020-06-019638110.3390/ijgi9060381Uncorrelated Geo-Text Inhibition Method Based on Voronoi K-Order and Spatial Correlations in Web MapsYufeng He0Yehua Sheng1Yunqing Jing2Yue Yin3Ahmad Hasnain4School of Geography, Nanjing Normal University, Nanjing 210023, ChinaSchool of Geography, Nanjing Normal University, Nanjing 210023, ChinaSchool of Geography, Nanjing Normal University, Nanjing 210023, ChinaSchool of Geography, Nanjing Normal University, Nanjing 210023, ChinaSchool of Geography, Nanjing Normal University, Nanjing 210023, ChinaUnstructured geo-text annotations volunteered by users of web map services enrich the basic geographic data. However, irrelevant geo-texts can be added to the web map, and these geo-texts reduce utility to users. Therefore, this study proposes a method to detect uncorrelated geo-text annotations based on Voronoi k-order neighborhood partition and auto-correlation statistical models. On the basis of the geo-text classification and semantic vector transformation, a quantitative description method for spatial autocorrelation was established by the Voronoi weighting method of inverse vicinity distance. The Voronoi k-order neighborhood self-growth strategy was used to detect the minimum convergence neighborhood for spatial autocorrelation. The Pearson method was used to calculate the correlation degree of the geo-text in the convergence region and then deduce the type of geo-text to be filtered. Experimental results showed that for given geo-text types in the study region, the proposed method effectively calculated the correlation between new geo-texts and the convergence region, providing an effective suggestion for preventing uncorrelated geo-text from uploading to the web map environment.https://www.mdpi.com/2220-9964/9/6/381geo-textspatial autocorrelationVoronoi k-ordervolunteered geographic informationsemantic analysistext auto-classification
spellingShingle Yufeng He
Yehua Sheng
Yunqing Jing
Yue Yin
Ahmad Hasnain
Uncorrelated Geo-Text Inhibition Method Based on Voronoi K-Order and Spatial Correlations in Web Maps
ISPRS International Journal of Geo-Information
geo-text
spatial autocorrelation
Voronoi k-order
volunteered geographic information
semantic analysis
text auto-classification
title Uncorrelated Geo-Text Inhibition Method Based on Voronoi K-Order and Spatial Correlations in Web Maps
title_full Uncorrelated Geo-Text Inhibition Method Based on Voronoi K-Order and Spatial Correlations in Web Maps
title_fullStr Uncorrelated Geo-Text Inhibition Method Based on Voronoi K-Order and Spatial Correlations in Web Maps
title_full_unstemmed Uncorrelated Geo-Text Inhibition Method Based on Voronoi K-Order and Spatial Correlations in Web Maps
title_short Uncorrelated Geo-Text Inhibition Method Based on Voronoi K-Order and Spatial Correlations in Web Maps
title_sort uncorrelated geo text inhibition method based on voronoi k order and spatial correlations in web maps
topic geo-text
spatial autocorrelation
Voronoi k-order
volunteered geographic information
semantic analysis
text auto-classification
url https://www.mdpi.com/2220-9964/9/6/381
work_keys_str_mv AT yufenghe uncorrelatedgeotextinhibitionmethodbasedonvoronoikorderandspatialcorrelationsinwebmaps
AT yehuasheng uncorrelatedgeotextinhibitionmethodbasedonvoronoikorderandspatialcorrelationsinwebmaps
AT yunqingjing uncorrelatedgeotextinhibitionmethodbasedonvoronoikorderandspatialcorrelationsinwebmaps
AT yueyin uncorrelatedgeotextinhibitionmethodbasedonvoronoikorderandspatialcorrelationsinwebmaps
AT ahmadhasnain uncorrelatedgeotextinhibitionmethodbasedonvoronoikorderandspatialcorrelationsinwebmaps