State of the Map 2021 - Academic Track

NLMaps Web is a web interface for querying OSM with natural language questions such as “Show me where I can find drinking water within 500m of the Louvre in Paris”. They are first parsed into a custom query language, which is then used to retrieve the answer by queries to Nominatim and Overpass.

Machine Learning is incredibly popular at this time among researchers working with OSM data and on OSM-related problems. But what impact has this work on ML had on the OSM database or OSM community? We investigate the impact on OSM, if any, the ML work within the academic research community has had over the last few years.

OpenStreetMap (OSM) constitutes a new open geographic database and offers several possibilities of adding local knowledge. While the importance of local knowledge is largely acknowledged in the OSM community, relatively few scientific studies have evaluated them. This study presents a framework to measure local data contribution in OSM in three case studies. The results highlight a framework for measuring local data in OSM as well as the distinct mapping stories of local OSM communities.

We look at interactions between Corporate and Non-Corporate Editors as reflected through co-editing patterns in the OSM data. We use Social Network Analysis on 12 networks generated from four different locations and 3 different timepoints and our results show the vibrant co-production of OSM data generation. There are interactions between all editors but Corporate Editors tend to interact at a higher rate with each other. The seniority of editors and the interactions also differ between Corporate and Non-Corporate Editors.

This talk presents results of an experiment conducted on the temporal accuracy of OpenStreetMap, and provides insights into the temporal dynamics with which changes in real-life appear in OSM.

It Consists in a proposal for a QGIS Plugin for Spatio-temporal analysis of OSM data quality in an area of Brazil.

We develop and test user embeddings approaches to vandalism detection in OSM. We successfully demonstrate improvements to previous vandalism detection methods, and additionally how the user embeddings can further be applied to detect different communities of mappers. We validated the embedding model with a prepared vandalism corpus that we are also releasing to the OSM community.

The rise of organized editing practices in the OpenStreetMap community has outpaced research methods for identifying mappers participating in these efforts and evaluating their work. This research uses machine-learning to improve upon prior approaches to estimating corporate editing on OSM, contributing both a novel methodology as well as summary statistics that shed light on corporate editing behavior in OSM.

During the past decades, the European Commission has invested billions in research through various programmes, such as H2020. In this study, we review exhaustively all the H2020 open deliverables to analyse how these public european projects are relying on OpenStreetMap.