Volume 8,Issue 9
Understanding of Floods by Analyzing Open-Source Data
This study investigates the reliability of Google Alerts as an open-source information source for flood emergency response. The study aims to determine whether reports about floods retrieved through Google Alerts provide consistent, accurate, and spatially relevant information. The study uses quantitative content analysis and a spatial and temporal research design. Fifty flood events are selected as the reference dataset. Numerical analysis is conducted to compare the number and timing of reports across these events. Natural language processing and named entity recognition are used to identify location information, including place names, rivers, roads, suburbs, and infrastructure. The extracted locations are standardized and compared with reference information for each event to assess content consistency, geographic accuracy, and reporting completeness. The results indicate variation in the number of reports retrieved across flood events. Earlier flood events generally produce fewer relevant reports than more recent events, suggesting that the availability of historical information is limited. Search outcomes are also influenced by keyword selection, the level of location detail, and the time at which the search is conducted. Despite these limitations, Google Alerts can identify specific towns and local infrastructure within affected areas. The reports also contain useful information on flood impacts, economic losses, disaster assessment, and recovery activities. These findings suggest that Google Alerts can provide a broad record of the social and economic consequences of floods, although its usefulness varies across events and time periods.
[1] Nearing G, Cohen D, Dube V, et al., 2024, Global Prediction of Extreme Floods in Ungauged Watersheds. Nature, 627(8004): 559–563. https://doi.org/10.1038/s41586024071451
[2] Das J, Manikanta V, Nikhil Teja K, et al., 2022, Two Decades of Ensemble Flood Forecasting: A State of the Art on Past Developments, Present Applications and Future Opportunities. Hydrological Sciences Journal, 67(3): 477–493. https://doi.org/10.1080/02626667.2021.2023157
[3] Rodriguez KM, Ofori SK, Bayliss LC, et al., 2020, Social Media Use in Emergency Response to Natural Disasters: A Systematic Review with a Public Health Perspective. Disaster Medicine and Public Health Preparedness, 14(1): 139–149. https://doi.org/10. 1017/dmp.2020.3
[6] Peng J, Zhang J, 2024, Spatiotemporal Assessment of Urban Flooding Hazard Using Social Media: A Case Study of Zhengzhou “7·20”. Environmental Modelling & Software, 2024(176): 106021.
[7] Szczepanek R, 2023, A Deep Learning Model of Spatial Distance and Named Entity Recognition (SD NER) for Flood Mark Text Classification. Water, 15(6): 1197.
[8] Tounsi A, Temimi M, 2023, A Systematic Review of Natural Language Processing Applications for Hydrometeorological Hazards Assessment. Natural Hazards, 116(3): 28192870.
[9] Sasaki Y, Tsuruoka Y, McNaught J, et al., 2008, How to Make the Most of NE Dictionaries in Statistical NER. BMC Bioinformatics, 9(Suppl 11): S5.
[10] Li J, Sun A, Han J, et al., 2020, A Survey on Deep Learning for Named Entity Recognition. IEEE Transactions on Knowledge and Data Engineering, 34(1): 50–70.
[11] Seow WL, Chaturvedi L, Hogarth A, et al., 2025, A Review of Named Entity Recognition: From Learning Methods to Modelling Paradigms and Tasks. Artificial Intelligence Review, 58(10): 315.
[12] Lai K, Porter JR, Amodeo M, et al., 2022, A Natural Language Processing Approach to Understanding Context in the Extraction and Geocoding of Historical Floods, Storms, and Adaptation Measures. Information Processing & Management, 59(1): 102735.
[13] Lawson N, Eustice K, Perkowitz M, et al., 2010, Annotating Large Email Datasets for Named Entity Recognition with Mechanical Turk. In Proceedings of the NAACLHLT 2010 workshop on creating speech and language data with Amazon’s Mechanical Turk (pp. 71–79).
[14] Islam MA, Rabbi F, Hossain NU, 2024, Performance Evaluation of NLP and CNN Models for Disaster Detection Using Social Media Data. Social Network Analysis and Mining, 14(1): 213. https://doi.org/10.1007/s13278-024-01374-y
[15] Sufi FK, Khalil L, 2022, Automated Disaster Monitoring From Social Media Posts Using AI-Based Location Intelligence and Sentiment Analysis. IEEE Transactions on Computational Social Systems, 11(4): 1–11.
[16] Kumar A, Singh JP, 2024, Deep Neural Networks for Location Reference Identification from Bilingual Disaster-Related Tweets. IEEE Transactions on Computational Social Systems, 2024(11): 880–891. https://doi.org/10.1109/TCSS.2022.3213702
[17] UCLouvain/CRED, 2026, Emergency Events Database (EM-DAT). Brussels, Belgium. https://www.emdat.be/