Toponymy Characteristics According to the Classification of Village Settlements by K-means Cluster Analysis: Case Study of Upper Northern Province Group

Abstract

In this research, geographic information systems are used in conjunction with statistical data. The objectives of this research were to classify village settlements in the upper northern region and analyze how the toponymy's features relate to its location and geographic features. Secondary data used are 8,549 village location data in the upper northern region, elevation model data, slope, water source, and major rivers. K-means cluster analysis to classify village settlements, statistical analysis using descriptive analysis, boxplot analysis to consider the distribution of comparative factors together with the use of geographic information systems for spatial analysis, and the principles of graph theory to show the relationship between characteristics.

The results of the study found that the villages were divided into 4 groups: 1) Villages are located on slightly undulating slopes, near rivers and water bodies. 2) Villages are located on undulating slopes, near rivers and water bodies. 3) Villages are located on slightly undulating slopes, near rivers and water bodies. on a slightly undulating area located near a water source but far from a river; and 4) Villages are located on a plateau on high ground and located far from rivers and water sources. The results of the analysis of the relationship between the name geography and location found that the history of the village names in each group More than 50 percent are related to location and geography.