{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/geotexttagger-high-precision-location-tagging","title":"GeoTextTagger: High-Precision Location Tagging of Textual Documents using a Natural Language Processing Approach","arxiv_id":"1601.05893","date":"2016-01-22","proceeding":null,"authors":["Shawn Brunsting","Hans De Sterck","Remco Dolman","Teun van Sprundel"],"abstract":"Location tagging, also known as geotagging or geolocation, is the process of\nassigning geographical coordinates to input data. In this paper we present an\nalgorithm for location tagging of textual documents. Our approach makes use of\nprevious work in natural language processing by using a state-of-the-art\npart-of-speech tagger and named entity recognizer to find blocks of text which\nmay refer to locations. A knowledge base (OpenStreatMap) is then used to find a\nlist of possible locations for each block. Finally, one location is chosen for\neach block by assigning distance-based scores to each location and repeatedly\nselecting the location and block with the best score. We tested our geolocation\nalgorithm with Wikipedia articles about topics with a well-defined geographical\nlocation that are geotagged by the articles' authors, where classification\napproaches have achieved median errors as low as 11 km, with attainable\naccuracy limited by the class size. Our approach achieved a 10th percentile\nerror of 490 metres and median error of 54 kilometres on the Wikipedia dataset\nwe used. When considering the five location tags with the greatest scores, 50%\nof articles were assigned at least one tag within 8.5 kilometres of the\narticle's author-assigned true location. We also tested our approach on Twitter\nmessages that are tagged with the location from which the message was sent.\nTwitter texts are challenging because they are short and unstructured and often\ndo not contain words referring to the location they were sent from, but we\nobtain potentially useful results. We explain how we use the Spark framework\nfor data analytics to collect and process our test data. In general,\nclassification-based approaches for location tagging may be reaching their\nupper accuracy limit, but our precision-focused approach has high accuracy for\nsome texts and shows significant potential for improvement overall.","url_abs":"http://arxiv.org/abs/1601.05893v1","url_pdf":"http://arxiv.org/pdf/1601.05893v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"geotexttagger-high-precision-location-tagging","repo_url":"https://github.com/spotzi/Geotagger","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"articles","task_name":"Articles"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"tag","task_name":"TAG"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}