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

Abstract

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

MSC-DeepFM: OSM Road Type Prediction via Integrating Spatial Context Using DeepFM

“…(4) The OSM Guangdong data are used for our experimental evaluation. The F1 score of our proposed model is 93.27%, which outperforms the existing tag recommendation model for OSM in the literature [9] and many state-of-the-art machine learning methods. Furthermore, the prediction accuracy of our model is obviously improved after integrating the features of intersecting roads.…”

“…To some extent, these issues have hindered the development of the OSM and reduced its role as a valuable source for monitoring some SDG indicators. Therefore, the research on how to improve the quality of OSM data [7][8][9] has been a popular topic in the academic community in recent years.…”

“…Most of them have focused on two aspects: quality evaluation [10][11][12] and quality improvement [7,13]. In terms of quality improvement, many scholars pay more attention to tag recommendations of OSM geographic objects [9,[14][15][16][17][18][19][20][21][22]. Existing tag recommendation methods are mostly based on the characteristics of OSM elements themselves [14][15][16][17][18][19].…”

“…Ali et al analyzed the spatial context of fuzzy grassland classification tag recommendation and counted the relevant regional entities, such as "amenities" and "leisure" and some linear entities in the research regions [21], in which the effectiveness of spatial context deployment has been verified. However, they did not adequately consider the in- Several studies have shown that it is feasible to extract spatial contexts (SC) and apply them to tag recommendation of spatial objects [9,[20][21][22], which can improve the recommendation accuracy in the case of poor data integrity and low semantic accuracy in OSM regions. Ali et al analyzed the spatial context of fuzzy grassland classification tag recommendation and counted the relevant regional entities, such as "amenities" and "leisure" and some linear entities in the research regions [21], in which the effectiveness of spatial context deployment has been verified.…”

A Large Scale Method for Extracting Geographical Features on Bus Routes From Openstreetmap and Assessment of Their Impact on Bus Speed and Reliability

“…While the aim of OSM is to produce a free world map, it has been used as a datasource in academic research (Grinberger et al, 2022). The quality of OSM data and possible ways of evaluating the quality has also been the focus of much research and the results of these studies vary by location and by application (Alghanim et al, 2021;Rabiei-Dastjerdi et al, 2020). To our knowledge, there are currently no studies evaluating the quality of OSM data as it pertains to the factors that influence bus performance.…”