Leveraging Road Characteristics and Contributor Behaviour for Assessing Road Type Quality in OSM

Volunteered Geographic Information (VGI) is often collected by non-expert users. This raises concerns about the quality and veracity of such data. There has been much effort to understand quantify VGI. Extrinsic measures which compare VGI authoritative data sources as National Mapping Agencies are common but cost slow update frequency hinder task. On other hand, intrinsic heuristics or models built from becoming increasingly popular. Supervised machine learning techniques particularly suitable for where they can infer predict properties spatial In this article we interested in assessing semantic information, road type, associated with OpenStreetMap (OSM). We have developed a approach utilises new input features dataset. Specifically, using our proposed novel obtained an average classification accuracy 84.12%. result outperforms existing on same inference The trustworthiness used developing training important. To address issue also measure direct indirect characteristics OSM its edit history along assessment users who contributed An evaluation impact determined be trustworthy within model shows that trusted improves prediction technique. results demonstrate 87.75% when applied dataset 57.98% untrusted Consequently, assess suggest improvements set.