{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,27]],"date-time":"2026-08-27T23:19:45Z","timestamp":1787872785466,"version":"build-2784847793"},"reference-count":28,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2026,8,28]],"date-time":"2026-08-28T00:00:00Z","timestamp":1787875200000},"content-version":"vor","delay-in-days":88,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["2117771"],"award-info":[{"award-number":["2117771"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Data"],"DOI":"10.1038\/s41597-026-07506-7","type":"journal-article","created":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T07:13:52Z","timestamp":1780298032000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A dataset from ten disasters for studying location descriptions and training AI models"],"prefix":"10.1038","volume":"13","author":[{"given":"Kai","family":"Sun","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yingjie","family":"Hu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kenneth","family":"Joseph","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,6,1]]},"reference":[{"key":"7506_CR1","doi-asserted-by":"publisher","first-page":"1549","DOI":"10.3390\/ijgi4031549","volume":"4","author":"Q Huang","year":"2015","unstructured":"Huang, Q. & Xiao, Y. Geographic situational awareness: mining tweets for disaster preparedness, emergency response, impact, and recovery. ISPRS Int. J. Geo-Inf. 4, 1549\u20131568 (2015).","journal-title":"ISPRS Int. J. Geo-Inf."},{"key":"7506_CR2","doi-asserted-by":"publisher","first-page":"1230","DOI":"10.1080\/17538947.2019.1574316","volume":"12","author":"M Yu","year":"2019","unstructured":"Yu, M., Huang, Q., Qin, H., Scheele, C. & Yang, C. Deep learning for real-time social media text classification for situation awareness \u2013 using Hurricanes Sandy, Harvey, and Irma as case studies. Int. J. Digit. Earth 12, 1230\u20131247 (2019).","journal-title":"Int. J. Digit. Earth"},{"key":"7506_CR3","doi-asserted-by":"crossref","unstructured":"Zou, L. et al. Social media for emergency rescue: An analysis of rescue requests on Twitter during Hurricane Harvey. Int. J. Disaster Risk Reduct. 103513 (2022).","DOI":"10.1016\/j.ijdrr.2022.103513"},{"key":"7506_CR4","doi-asserted-by":"publisher","first-page":"101824","DOI":"10.1016\/j.compenvurbsys.2022.101824","volume":"95","author":"B Zhou","year":"2022","unstructured":"Zhou, B. et al. VictimFinder: Harvesting rescue requests in disaster response from social media with BERT. Comput. Environ. Urban Syst. 95, 101824 (2022).","journal-title":"Comput. Environ. Urban Syst."},{"key":"7506_CR5","doi-asserted-by":"publisher","first-page":"933","DOI":"10.1609\/icwsm.v15i1.18116","volume":"15","author":"F Alam","year":"2021","unstructured":"Alam, F., Qazi, U., Imran, M. & Ofli, F. Humaid: Human-annotated disaster incidents data from twitter with deep learning benchmarks. Proceedings of the International AAAI Conference on Web and social media 15, 933\u2013942 (2021).","journal-title":"Proceedings of the International AAAI Conference on Web and social media"},{"key":"7506_CR6","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1080\/13658816.2017.1368523","volume":"32","author":"JO Wallgr\u00fcn","year":"2018","unstructured":"Wallgr\u00fcn, J. O., Karimzadeh, M., MacEachren, A. M. & Pezanowski, S. GeoCorpora: building a corpus to test and train microblog geoparsers. Int. J. Geogr. Inf. Sci. 32, 1\u201329 (2018).","journal-title":"Int. J. Geogr. Inf. Sci."},{"key":"7506_CR7","doi-asserted-by":"publisher","first-page":"103742","DOI":"10.1016\/j.ipm.2024.103742","volume":"61","author":"X Hu","year":"2024","unstructured":"Hu, X. et al. DLRGeoTweet: A comprehensive social media geocoding corpus featuring fine-grained places. Inf. Process. Manag. 61, 103742 (2024).","journal-title":"Inf. Process. Manag."},{"key":"7506_CR8","doi-asserted-by":"publisher","first-page":"103340","DOI":"10.1016\/j.ipm.2023.103340","volume":"60","author":"R Suwaileh","year":"2023","unstructured":"Suwaileh, R., Elsayed, T. & Imran, M. IDRISI-RE: A generalizable dataset with benchmarks for location mention recognition on disaster tweets. Inf. Process. Manag. 60, 103340 (2023).","journal-title":"Inf. Process. Manag."},{"key":"7506_CR9","unstructured":"Hu, Y. & Wang, J. How do people describe locations during a natural disaster: an analysis of tweets from Hurricane Harvey. in Proceedings of the 11th International Conference on Geographic Information Science (Poznan, Poland, 2021)."},{"key":"7506_CR10","doi-asserted-by":"publisher","first-page":"2289","DOI":"10.1080\/13658816.2023.2266495","volume":"37","author":"Y Hu","year":"2023","unstructured":"Hu, Y. et al. Geo-knowledge-guided GPT models improve the extraction of location descriptions from disaster-related social media messages. Int. J. Geogr. Inf. Sci. 37, 2289\u20132318 (2023).","journal-title":"Int. J. Geogr. Inf. Sci."},{"key":"7506_CR11","doi-asserted-by":"publisher","first-page":"117","DOI":"10.32714\/ricl.10.01.06","volume":"10","author":"NJ Fern\u00e1ndez-Mart\u00ednez","year":"2022","unstructured":"Fern\u00e1ndez-Mart\u00ednez, N. J. The FGLOCTweet Corpus: An English tweet-based corpus for fine-grained location-detection tasks. Res. Corpus Linguist. 10, 117\u2013133 (2022).","journal-title":"Res. Corpus Linguist."},{"key":"7506_CR12","doi-asserted-by":"publisher","first-page":"635","DOI":"10.1007\/s10707-012-0173-8","volume":"17","author":"J Gelernter","year":"2013","unstructured":"Gelernter, J. & Balaji, S. An algorithm for local geoparsing of microtext. GeoInformatica 17, 635\u2013667 (2013).","journal-title":"GeoInformatica"},{"key":"7506_CR13","doi-asserted-by":"publisher","first-page":"161","DOI":"10.3390\/ijgi8040161","volume":"8","author":"M Karimzadeh","year":"2019","unstructured":"Karimzadeh, M. & MacEachren, A. M. GeoAnnotator: a collaborative semi-automatic platform for constructing geo-annotated text corpora. ISPRS Int. J. Geo-Inf. 8, 161 (2019).","journal-title":"ISPRS Int. J. Geo-Inf."},{"key":"7506_CR14","unstructured":"Longley, P. A., Goodchild, M. F., Maguire, D. J. & Rhind, D. W. Geographic Information Systems and Science. (John Wiley & Sons, 2005)."},{"key":"7506_CR15","doi-asserted-by":"publisher","unstructured":"Sun, K., Hu, Y., Joseph, K. & Zhou, R. Z. GALLOC: a GeoAnnotator for Labeling LOCation descriptions from disaster-related text messages. Int. J. Geogr. Inf. Sci. 1\u201331, https:\/\/doi.org\/10.1080\/13658816.2025.2464643 (2025).","DOI":"10.1080\/13658816.2025.2464643"},{"key":"7506_CR16","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2771588","volume":"47","author":"M Imran","year":"2015","unstructured":"Imran, M., Castillo, C., Diaz, F. & Vieweg, S. Processing social media messages in mass emergency: A survey. ACM Comput. Surv. CSUR 47, 1\u201338 (2015).","journal-title":"ACM Comput. Surv. CSUR"},{"key":"7506_CR17","doi-asserted-by":"publisher","first-page":"1393","DOI":"10.1111\/tgis.12579","volume":"23","author":"J Wang","year":"2019","unstructured":"Wang, J. & Hu, Y. Enhancing spatial and textual analysis with EUPEG: An extensible and unified platform for evaluating geoparsers. Trans. GIS 23, 1393\u20131419 (2019).","journal-title":"Trans. GIS"},{"key":"7506_CR18","doi-asserted-by":"publisher","DOI":"10.6084\/m9.figshare.31044040.v2","author":"K Sun","year":"2026","unstructured":"Sun, K., Hu, Y. & Joseph, K. A dataset from ten disasters for studying location descriptions and training AI models. Figshare https:\/\/doi.org\/10.6084\/m9.figshare.31044040.v2 (2026)."},{"key":"7506_CR19","doi-asserted-by":"publisher","first-page":"103107","DOI":"10.1016\/j.ijdrr.2022.103107","volume":"78","author":"R Suwaileh","year":"2022","unstructured":"Suwaileh, R., Elsayed, T., Imran, M. & Sajjad, H. When a disaster happens, we are ready: Location mention recognition from crisis tweets. Int. J. Disaster Risk Reduct. 78, 103107 (2022).","journal-title":"Int. J. Disaster Risk Reduct."},{"key":"7506_CR20","unstructured":"Brandsen, A., Verberne, S., Wansleeben, M. & Lambers, K. Creating a dataset for named entity recognition in the archaeology domain. in Proceedings of the Twelfth Language Resources and Evaluation Conference 4573\u20134577 (2020)."},{"key":"7506_CR21","doi-asserted-by":"crossref","unstructured":"Nowak, S. & R\u00fcger, S. How reliable are annotations via crowdsourcing: a study about inter-annotator agreement for multi-label image annotation. In Proceedings of the international conference on Multimedia information retrieval 557\u2013566 (2010).","DOI":"10.1145\/1743384.1743478"},{"key":"7506_CR22","doi-asserted-by":"publisher","first-page":"276","DOI":"10.11613\/BM.2012.031","volume":"22","author":"ML McHugh","year":"2012","unstructured":"McHugh, M. L. Interrater reliability: the kappa statistic. Biochem. Medica 22, 276\u2013282 (2012).","journal-title":"Biochem. Medica"},{"key":"7506_CR23","doi-asserted-by":"crossref","unstructured":"Basile, V. et al. We need to consider disagreement in evaluation. In Proceedings of the 1st workshop on benchmarking: past, present and future 15\u201321 (Association for Computational Linguistics, 2021).","DOI":"10.18653\/v1\/2021.bppf-1.3"},{"key":"7506_CR24","doi-asserted-by":"crossref","unstructured":"Fornaciari, T. et al. Beyond black & white: Leveraging annotator disagreement via soft-label multi-task learning. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Association for Computational Linguistics, 2021).","DOI":"10.18653\/v1\/2021.naacl-main.204"},{"key":"7506_CR25","doi-asserted-by":"crossref","unstructured":"Fleisig, E., Blodgett, S. L., Klein, D. & Talat, Z. The Perspectivist Paradigm Shift: Assumptions and Challenges of Capturing Human Labels. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers) 2279\u20132292 (2024).","DOI":"10.18653\/v1\/2024.naacl-long.126"},{"key":"7506_CR26","doi-asserted-by":"crossref","unstructured":"Zhang, W. & Gelernter, J. Geocoding location expressions in Twitter messages: A preference learning method. J. Spat. Inf. Sci. 37\u201370 (2014).","DOI":"10.5311\/JOSIS.2014.9.170"},{"key":"7506_CR27","doi-asserted-by":"publisher","first-page":"164","DOI":"10.1561\/1500000034","volume":"12","author":"RS Purves","year":"2018","unstructured":"Purves, R. S., Clough, P., Jones, C. B., Hall, M. H. & Murdock, V. Geographic information retrieval: Progress and challenges in spatial search of text. Found. Trends\u00ae Inf. Retr. 12, 164\u2013318 (2018).","journal-title":"Found. Trends\u00ae Inf. Retr."},{"key":"7506_CR28","doi-asserted-by":"publisher","first-page":"683","DOI":"10.1007\/s10579-019-09475-3","volume":"54","author":"M Gritta","year":"2020","unstructured":"Gritta, M., Pilehvar, M. T. & Collier, N. A pragmatic guide to geoparsing evaluation. Lang. Resour. Eval. 54, 683\u2013712 (2020).","journal-title":"Lang. Resour. Eval."}],"container-title":["Scientific Data"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41597-026-07506-7","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41597-026-07506-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41597-026-07506-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,27]],"date-time":"2026-08-27T22:57:56Z","timestamp":1787871476000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41597-026-07506-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,1]]},"references-count":28,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["7506"],"URL":"https:\/\/doi.org\/10.1038\/s41597-026-07506-7","relation":{"references":[{"id-type":"doi","id":"10.6084\/m9.figshare.31044040.v2","asserted-by":"subject"}]},"ISSN":["2052-4463"],"issn-type":[{"value":"2052-4463","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,1]]},"assertion":[{"value":"15 October 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 May 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 June 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","label":"Competing interests","group":{"name":"EthicsHeading","label":"Ethics"}}],"article-number":"1242"}}