SPOT: Bridging Natural Language and Geospatial Search for Investigative Journalists
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912432379658240 |
|---|---|
| author | Khellaf, Lynn Schlicht, Ipek Baris Mirass, Tilman Bayer, Julia Wagner, Tilman Bouwmeester, Ruben |
| author_facet | Khellaf, Lynn Schlicht, Ipek Baris Mirass, Tilman Bayer, Julia Wagner, Tilman Bouwmeester, Ruben |
| contents | OpenStreetMap (OSM) is a vital resource for investigative journalists doing geolocation verification. However, existing tools to query OSM data such as Overpass Turbo require familiarity with complex query languages, creating barriers for non-technical users. We present SPOT, an open source natural language interface that makes OSM's rich, tag-based geographic data more accessible through intuitive scene descriptions. SPOT interprets user inputs as structured representations of geospatial object configurations using fine-tuned Large Language Models (LLMs), with results being displayed in an interactive map interface. While more general geospatial search tasks are conceivable, SPOT is specifically designed for use in investigative journalism, addressing real-world challenges such as hallucinations in model output, inconsistencies in OSM tagging, and the noisy nature of user input. It combines a novel synthetic data pipeline with a semantic bundling system to enable robust, accurate query generation. To our knowledge, SPOT is the first system to achieve reliable natural language access to OSM data at this level of accuracy. By lowering the technical barrier to geolocation verification, SPOT contributes a practical tool to the broader efforts to support fact-checking and combat disinformation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_13188 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SPOT: Bridging Natural Language and Geospatial Search for Investigative Journalists Khellaf, Lynn Schlicht, Ipek Baris Mirass, Tilman Bayer, Julia Wagner, Tilman Bouwmeester, Ruben Information Retrieval Computation and Language Human-Computer Interaction OpenStreetMap (OSM) is a vital resource for investigative journalists doing geolocation verification. However, existing tools to query OSM data such as Overpass Turbo require familiarity with complex query languages, creating barriers for non-technical users. We present SPOT, an open source natural language interface that makes OSM's rich, tag-based geographic data more accessible through intuitive scene descriptions. SPOT interprets user inputs as structured representations of geospatial object configurations using fine-tuned Large Language Models (LLMs), with results being displayed in an interactive map interface. While more general geospatial search tasks are conceivable, SPOT is specifically designed for use in investigative journalism, addressing real-world challenges such as hallucinations in model output, inconsistencies in OSM tagging, and the noisy nature of user input. It combines a novel synthetic data pipeline with a semantic bundling system to enable robust, accurate query generation. To our knowledge, SPOT is the first system to achieve reliable natural language access to OSM data at this level of accuracy. By lowering the technical barrier to geolocation verification, SPOT contributes a practical tool to the broader efforts to support fact-checking and combat disinformation. |
| title | SPOT: Bridging Natural Language and Geospatial Search for Investigative Journalists |
| topic | Information Retrieval Computation and Language Human-Computer Interaction |
| url | https://arxiv.org/abs/2506.13188 |