Semantic Similarity Assessment of Volunteered Geographic Information


The recent development in communication technologies between individuals allows for the establishment of more informal collaborative map data projects which are called volunteered geographic information (VGI). These projects, such as OpenStreetMap (OSM) project, seek to create free alternative maps which let users add or input new materials to the data of others. The information of different VGI data sources is often not compliant to any standard and each organization is producing a dataset at various level of richness. In this research the assessment of semantic data quality provided by web sources, e.g. OSM will depend on a comparison with the information from standard sources. This will include the validity of semantic accuracy as one of the most important parameter of spatial data quality parameters. Semantic similarity testing covered feature classification, in effect comparing possible categories (legend classes) and actual attributes attached to features. This will be achieved by developing a tool, using Matlab programming language, for analysing and examining OSM semantic accuracy. To identify the strength of semantic accuracy assessment strategy, there are many factors should be considered. For instance, the confusion matrix of feature classifications can be assessed, and different statistical tests should be passed. The results revealed good semantic accuracy of OSM datasets.