{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,13]],"date-time":"2026-05-13T17:30:04Z","timestamp":1778693404878,"version":"3.51.4"},"reference-count":54,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,5,7]],"date-time":"2025-05-07T00:00:00Z","timestamp":1746576000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,5,7]],"date-time":"2025-05-07T00:00:00Z","timestamp":1746576000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Soc. Netw. Anal. Min."],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>During large-scale disasters, emergency call centers are often overwhelmed by the large volume of rescue requests and calls for help. Consequently, people are turning to social media platforms to seek assistance. Rescue information posted on these platforms is extremely valuable for first responders to make informed rescue decisions. Therefore, the automatic identification of these requests from the vast amount of data posted on social media during crises is critical yet challenging. This work presents our ongoing research on applying deep learning techniques to extract actionable rescue information from social media during crises. We proposed a novel deep learning model that integrates a fine-tuned BERT to extract low-level statistical features and rule-based Regex filters to extract problem-specific features for emergency tweet identification. The proposed model was evaluated on labeled tweets collected from three hurricane events (Harvey, Ian, and Ida). Experimental results showed that our model performed better than several machine learning and deep learning methods in terms of the Area Under the Precision-Recall Curve (AUC-PR) metric for all events. This study contributed to the crisis informatics literature by introducing a novel deep learning approach for automatically identifying actionable information in social media, which can be adapted for similar natural language processing (NLP) tasks.<\/jats:p>","DOI":"10.1007\/s13278-025-01462-7","type":"journal-article","created":{"date-parts":[[2025,5,7]],"date-time":"2025-05-07T07:15:56Z","timestamp":1746602156000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["An integrated machine learning approach for identifying emergency rescue messages on social media during natural disasters"],"prefix":"10.1007","volume":"15","author":[{"given":"Wael","family":"Khallouli","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiang","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jingwei","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ghaith","family":"Rabadi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Samuel","family":"Kovacic","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,5,7]]},"reference":[{"key":"1462_CR1","doi-asserted-by":"crossref","unstructured":"Ahmad K, Riegler M, Pogorelov K, et\u00a0al (2017) Jord: a system for collecting information and monitoring natural disasters by linking social media with satellite imagery. In: Proceedings of the 15th international workshop on content-based multimedia indexing, pp 1\u20136","DOI":"10.1145\/3095713.3095726"},{"key":"1462_CR2","doi-asserted-by":"crossref","unstructured":"Akiba T, Sano S, Yanase T et\u00a0al (2019) Optuna: A next-generation hyperparameter optimization framework. In: Proceedings of the 25rd ACM SIGKDD international conference on knowledge discovery and data mining","DOI":"10.1145\/3292500.3330701"},{"key":"1462_CR3","doi-asserted-by":"crossref","unstructured":"Alshehri A, Alahamri S (2019) An ensemble learning for detecting situational awareness tweets during environmental hazards. In: 2019 IEEE international systems conference (SysCon), IEEE, pp 1\u20138","DOI":"10.1109\/SYSCON.2019.8836814"},{"issue":"3","key":"1462_CR4","doi-asserted-by":"publisher","first-page":"604","DOI":"10.1109\/TCSS.2019.2914179","volume":"6","author":"M Basu","year":"2019","unstructured":"Basu M, Shandilya A, Khosla P et al (2019) Extracting resource needs and availabilities from microblogs for aiding post-disaster relief operations. IEEE Trans Comput Soc Syst 6(3):604\u2013618","journal-title":"IEEE Trans Comput Soc Syst"},{"key":"1462_CR5","doi-asserted-by":"publisher","first-page":"185842","DOI":"10.1109\/ACCESS.2020.3030184","volume":"8","author":"UA Bukar","year":"2020","unstructured":"Bukar UA, Jabar MA, Sidi F et al (2020) Crisis informatics in the context of social media crisis communication: theoretical models, taxonomy, and open issues. IEEE Access 8:185842\u2013185869","journal-title":"IEEE Access"},{"key":"1462_CR6","unstructured":"Caragea C, Silvescu A, Tapia AH (2016) Identifying informative messages in disaster events using convolutional neural networks. In: International conference on information systems for crisis response and management, pp 137\u2013147"},{"key":"1462_CR7","unstructured":"Coche J, Kropczynski J, Montarnal A, et\u00a0al (2021) Actionability in a situation awareness world: Implications for social media processing system design. In: ISCRAM 2021-18th international conference on information systems for crisis response and management, 2391, pp p\u2013994"},{"key":"1462_CR8","unstructured":"Cowan J (2017) When 911 failed them, desperate harvey victims turned to social media for help. https:\/\/www.dallasnews.com\/news\/weather\/2017\/08\/27\/when-911-failed-them-desperate-harvey-victims-turned-to-social-media-for-help\/, accessed: 2020-09-10"},{"key":"1462_CR9","unstructured":"Coyne M (2023) Service assessment august-september 2021 hurricane ida. https:\/\/www.weather.gov\/media\/publications\/assessments\/Hurricane_Ida_Service_Assessment.pdf, accessed: 2023-08-28"},{"key":"1462_CR10","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijdrr.2021.102043","volume":"54","author":"JS Dargin","year":"2021","unstructured":"Dargin JS, Fan C, Mostafavi A (2021) Vulnerable populations and social media use in disasters: Uncovering the digital divide in three major us hurricanes. Int J Disaster Risk Reduct 54:102043","journal-title":"Int J Disaster Risk Reduct"},{"key":"1462_CR11","doi-asserted-by":"crossref","unstructured":"Davis J, Goadrich M (2006) The relationship between precision-recall and roc curves. In: Proceedings of the 23rd international conference on Machine learning, pp 233\u2013240","DOI":"10.1145\/1143844.1143874"},{"key":"1462_CR12","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijdrr.2020.101757","volume":"51","author":"A Devaraj","year":"2020","unstructured":"Devaraj A, Murthy D, Dontula A (2020) Machine-learning methods for identifying social media-based requests for urgent help during hurricanes. Int J Disaster Risk Reduct 51:101757","journal-title":"Int J Disaster Risk Reduct"},{"key":"1462_CR13","unstructured":"Devlin J, Chang MW, Lee K et\u00a0al (2018) Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805"},{"issue":"5","key":"1462_CR14","doi-asserted-by":"publisher","first-page":"526","DOI":"10.1080\/1553118X.2018.1510405","volume":"12","author":"M Eriksson","year":"2018","unstructured":"Eriksson M (2018) Lessons for crisis communication on social media: a systematic review of what research tells the practice. Int J Strateg Commun 12(5):526\u2013551","journal-title":"Int J Strateg Commun"},{"key":"1462_CR15","doi-asserted-by":"publisher","DOI":"10.1016\/j.compenvurbsys.2020.101514","volume":"83","author":"C Fan","year":"2020","unstructured":"Fan C, Esparza M, Dargin J et al (2020) Spatial biases in crowdsourced data: social media content attention concentrates on populous areas in disasters. Comput Environ Urban Syst 83:101514","journal-title":"Comput Environ Urban Syst"},{"issue":"2","key":"1462_CR16","doi-asserted-by":"publisher","first-page":"97","DOI":"10.1515\/jhsem-2021-0042","volume":"20","author":"C Garcia","year":"2023","unstructured":"Garcia C, Rabadi G, Abujaber D et al (2023) Supporting humanitarian crisis decision making with reliable intelligence derived from social media using ai. J Homel Secur Emerg Manage 20(2):97\u2013131","journal-title":"J Homel Secur Emerg Manage"},{"issue":"1","key":"1462_CR17","doi-asserted-by":"publisher","first-page":"151","DOI":"10.1007\/s13278-024-01323-9","volume":"14","author":"PK Garg","year":"2024","unstructured":"Garg PK, Chakraborty R, Dandapat SK (2024) Adsumm: annotated ground-truth summary datasets for disaster tweet summarization. Soc Netw Anal Min 14(1):151","journal-title":"Soc Netw Anal Min"},{"issue":"39","key":"1462_CR18","doi-asserted-by":"publisher","first-page":"1385","DOI":"10.15585\/mmwr.mm7039a3","volume":"70","author":"A Hanchey","year":"2021","unstructured":"Hanchey A, Schnall A, Bayleyegn T et al (2021) Notes from the field: deaths related to hurricane ida reported by media\u2014nine states, august 29-september 9, 2021. Morb Mortal Wkly Rep 70(39):1385","journal-title":"Morb Mortal Wkly Rep"},{"issue":"2","key":"1462_CR19","doi-asserted-by":"publisher","first-page":"124","DOI":"10.1504\/IJCIS.2023.130455","volume":"19","author":"J Huang","year":"2023","unstructured":"Huang J, Khallouli W, Rabadi G et al (2023) Intelligent agent for hurricane emergency identification and text information extraction from streaming social media big data. Int J Crit Infrastruct 19(2):124\u2013139","journal-title":"Int J Crit Infrastruct"},{"key":"1462_CR20","doi-asserted-by":"crossref","unstructured":"Imran M, Elbassuoni S, Castillo C, et\u00a0al (2013) Practical extraction of disaster-relevant information from social media. In: Proceedings of the 22nd international conference on world wide web, pp 1021\u20131024","DOI":"10.1145\/2487788.2488109"},{"issue":"5","key":"1462_CR21","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2020.102261","volume":"57","author":"M Imran","year":"2020","unstructured":"Imran M, Ofli F, Caragea D et al (2020) Using ai and social media multimodal content for disaster response and management: opportunities, challenges, and future directions. Inf Process Manag 57(5):102261","journal-title":"Inf Process Manag"},{"key":"1462_CR22","doi-asserted-by":"crossref","unstructured":"Kabir MY, Madria S (2019) A deep learning approach for tweet classification and rescue scheduling for effective disaster management. In: Proceedings of the 27th ACM SIGSPATIAL international conference on advances in geographic information systems, pp 269\u2013278","DOI":"10.1145\/3347146.3359097"},{"key":"1462_CR23","unstructured":"Kevin S, Robert S, Emily WT (2017) More than 30,000 people expected in shelters as extent of harvey\u2019s blow comes into chilling focus. https:\/\/www.washingtonpost.com\/politics\/full-extent-of-harveys-aftermath-starts-to-come-into-chilling-focus\/2017\/08\/27\/1b2b184a-8b56-11e7-8df5-c2e5cf46c1e2_story.html, accessed: 2023-08-28"},{"key":"1462_CR24","doi-asserted-by":"publisher","unstructured":"Kim Y (2014) Convolutional neural networks for sentence classification. https:\/\/doi.org\/10.48550\/ARXIV.1408.5882, https:\/\/arxiv.org\/abs\/1408.5882","DOI":"10.48550\/ARXIV.1408.5882"},{"key":"1462_CR25","doi-asserted-by":"crossref","unstructured":"Kumar A, Singh JP, Dwivedi YK, et\u00a0al (2020) A deep multi-modal neural network for informative twitter content classification during emergencies. Ann Opera Res pp 1\u201332","DOI":"10.1007\/s10479-020-03514-x"},{"key":"1462_CR26","doi-asserted-by":"publisher","first-page":"647","DOI":"10.1016\/j.chb.2015.05.027","volume":"54","author":"KA Lachlan","year":"2016","unstructured":"Lachlan KA, Spence PR, Lin X et al (2016) Social media and crisis management: Cerc, search strategies, and twitter content. Comput Hum Behav 54:647\u2013652","journal-title":"Comput Hum Behav"},{"key":"1462_CR27","doi-asserted-by":"publisher","first-page":"601","DOI":"10.1016\/j.chb.2016.05.080","volume":"65","author":"X Lin","year":"2016","unstructured":"Lin X, Spence PR, Sellnow TL et al (2016) Crisis communication, learning and responding: best practices in social media. Comput Hum Behav 65:601\u2013605","journal-title":"Comput Hum Behav"},{"key":"1462_CR28","unstructured":"Lisa B, Laura A, Andrew H, et\u00a0al (2023) National hurricane center tropical cyclone report: Hurricane ian. National Hurricane Center"},{"key":"1462_CR29","doi-asserted-by":"crossref","unstructured":"Liu J, Singhal T, Blessing L, et\u00a0al (2020) Crisisbert: a robust transformer for crisis classification and contextual crisis embedding. arXiv preprint arXiv:2005.06627","DOI":"10.1145\/3465336.3475117"},{"key":"1462_CR30","doi-asserted-by":"crossref","unstructured":"Madianou M (2015) Digital inequality and second-order disasters: Social media in the typhoon haiyan recovery. Social Media+ Society 1(2):2056305115603386","DOI":"10.1177\/2056305115603386"},{"issue":"1","key":"1462_CR31","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s13278-019-0579-5","volume":"9","author":"S Madichetty","year":"2019","unstructured":"Madichetty S, Sridevi M (2019) Disaster damage assessment from the tweets using the combination of statistical features and informative words. Soc Netw Anal Min 9(1):1\u201311","journal-title":"Soc Netw Anal Min"},{"issue":"4","key":"1462_CR32","doi-asserted-by":"publisher","first-page":"870","DOI":"10.1109\/TCSS.2021.3064299","volume":"8","author":"S Madichetty","year":"2021","unstructured":"Madichetty S, Sridevi M (2021) A neural-based approach for detecting the situational information from twitter during disaster. IEEE Trans Comput Soc Syst 8(4):870\u2013880","journal-title":"IEEE Trans Comput Soc Syst"},{"key":"1462_CR33","doi-asserted-by":"crossref","unstructured":"Madichetty S, Muthukumarasamy S, Jayadev P (2021) Multi-modal classification of twitter data during disasters for humanitarian response. Journal of Ambient Intelligence and Humanized Computing pp 1\u201315","DOI":"10.1007\/s12652-020-02791-5"},{"key":"1462_CR34","first-page":"196","volume":"43","author":"M Mart\u00ednez-Rojas","year":"2018","unstructured":"Mart\u00ednez-Rojas M, del Carmen Pardo-Ferreira M, Rubio-Romero JC (2018) Twitter as a tool for the management and analysis of emergency situations: A systematic literature review. Int J Inf Manage 43:196\u2013208","journal-title":"Int J Inf Manage"},{"key":"1462_CR35","unstructured":"National 911 Program (2011) History of 911 and what it means for the future of emergency communications. https:\/\/www.911.gov\/assets\/History-of-911-And-What-It-Means-for-the-Future-of-Emergency-Communications.pdf, accessed: 2024-12-21"},{"key":"1462_CR36","doi-asserted-by":"crossref","unstructured":"Nazer TH, Morstatter F, Dani H, et\u00a0al (2016) Finding requests in social media for disaster relief. In: 2016 IEEE\/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM), IEEE, pp 1410\u20131413","DOI":"10.1109\/ASONAM.2016.7752432"},{"key":"1462_CR37","unstructured":"NIOSH (2019) Emergency response resources. https:\/\/www.cdc.gov\/niosh\/topics\/emres\/natural.html, accessed: 2023-01-08"},{"key":"1462_CR38","doi-asserted-by":"crossref","unstructured":"Olteanu A, Castillo C, Diaz F, et\u00a0al (2014) Crisislex: A lexicon for collecting and filtering microblogged communications in crises. In: Proceedings of the International AAAI Conference on Web and Social Media","DOI":"10.1609\/icwsm.v8i1.14538"},{"key":"1462_CR39","unstructured":"Pandey R, Purohit H, Chan J, et\u00a0al (2018) Ai for trustworthiness! credible user identification on social web for disaster response agencies. AAAI FSS-18: Artificial Intelligence in Government and Public Sector Proceedings"},{"key":"1462_CR40","doi-asserted-by":"crossref","unstructured":"Pennington J, Socher R, Manning CD (2014) Glove: Global vectors for word representation. In: Proceedings of the 2014 conference on empirical methods in natural language processing (EMNLP), pp 1532\u20131543","DOI":"10.3115\/v1\/D14-1162"},{"key":"1462_CR41","unstructured":"Security H (2012) Social media strategy virtual social media working group and dhs first responders group. https:\/\/www.dhs.gov\/sites\/default\/files\/publications\/Virtual%20Social%20Media%20Working%20Group%20VSMWG%20Social%20Media%20Strategy.pdf"},{"key":"1462_CR42","unstructured":"Sedensky M (2017) \u2019hell\u2019s breaking loose\u2019: A 911 center under siege by harvey. https:\/\/apnews.com\/article\/hurricane-harvey-us-news-ap-top-news-houston-storms-14ef84b1750a44de943b27414a030156, accessed: 2021-06-07"},{"key":"1462_CR43","doi-asserted-by":"crossref","unstructured":"Sit MA, Koylu C, Demir I (2019) Identifying disaster-related tweets and their semantic, spatial and temporal context using deep learning, natural language processing and spatial analysis: a case study of hurricane irma. International Journal of Digital Earth","DOI":"10.4324\/9781003106494-2"},{"key":"1462_CR44","unstructured":"Statistica (2021) Most expensive natural disasters in the united states as of june 2021. https:\/\/www.statista.com\/statistics\/744015\/most-expensive-natural-disasters-usa\/, accessed: 2021-06-06"},{"key":"1462_CR45","unstructured":"Tanev H, Zavarella V, Steinberger J (2017) Monitoring disaster impact: detecting micro-events and eyewitness reports in mainstream and social media. In: ISCRAM"},{"key":"1462_CR46","doi-asserted-by":"publisher","first-page":"483","DOI":"10.1007\/s10606-014-9206-1","volume":"23","author":"AH Tapia","year":"2014","unstructured":"Tapia AH, Moore K (2014) Good enough is good enough: overcoming disaster response organizations\u2019 slow social media data adoption. Comput Support Cooperative Work (CSCW) 23:483\u2013512","journal-title":"Comput Support Cooperative Work (CSCW)"},{"key":"1462_CR47","unstructured":"Tribune TT (2017) State says harvey\u2019s death toll has reached 88. https:\/\/www.texastribune.org\/2017\/10\/13\/harveys-death-toll-reaches-93-people\/, accessed: 2021-06-07"},{"key":"1462_CR48","unstructured":"Vaswani A, Shazeer N, Parmar N, et\u00a0al (2017) Attention is all you need. In: Advances in neural information processing systems, pp 5998\u20136008"},{"issue":"11","key":"1462_CR49","doi-asserted-by":"publisher","first-page":"570","DOI":"10.3390\/ijgi11110570","volume":"11","author":"Z Wang","year":"2022","unstructured":"Wang Z, Lam NS, Sun M et al (2022) A machine learning approach for detecting rescue requests from social media. ISPRS Int J Geo Inf 11(11):570","journal-title":"ISPRS Int J Geo Inf"},{"issue":"11","key":"1462_CR50","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 et al (2019) Deep learning for real-time social media text classification for situation awareness-using hurricanes sandy, harvey, and irma as case studies. Int J Digital Earth 12(11):1230\u20131247","journal-title":"Int J Digital Earth"},{"key":"1462_CR51","doi-asserted-by":"crossref","unstructured":"Zade H, Shah K, Rangarajan V, et\u00a0al (2018a) From situational awareness to actionability: Towards improving the utility of social media data for crisis response. Proceedings of the ACM on human-computer interaction 2(CSCW):1\u201318","DOI":"10.1145\/3274464"},{"key":"1462_CR52","doi-asserted-by":"crossref","unstructured":"Zade H, Shah K, Rangarajan V, et\u00a0al (2018b) From situational awareness to actionability: Towards improving the utility of social media data for crisis response. Proceedings of the ACM on human-computer interaction 2(CSCW):1\u201318","DOI":"10.1145\/3274464"},{"key":"1462_CR53","doi-asserted-by":"crossref","unstructured":"Zahera HM, Elgendy IA, Jalota R, et\u00a0al (2019) Fine-tuned bert model for multi-label tweets classification. In: TREC, pp 1\u20137","DOI":"10.6028\/NIST.SP.1250.incident-DICE_UPB"},{"key":"1462_CR54","doi-asserted-by":"publisher","DOI":"10.1016\/j.compenvurbsys.2022.101824","volume":"95","author":"B Zhou","year":"2022","unstructured":"Zhou B, Zou L, Mostafavi A et al (2022) Victimfinder: harvesting rescue requests in disaster response from social media with bert. Comput Environ Urban Syst 95:101824","journal-title":"Comput Environ Urban Syst"}],"container-title":["Social Network Analysis and Mining"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13278-025-01462-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s13278-025-01462-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13278-025-01462-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,17]],"date-time":"2025-12-17T08:27:50Z","timestamp":1765960070000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s13278-025-01462-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,7]]},"references-count":54,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["1462"],"URL":"https:\/\/doi.org\/10.1007\/s13278-025-01462-7","relation":{},"ISSN":["1869-5469"],"issn-type":[{"value":"1869-5469","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5,7]]},"assertion":[{"value":"12 July 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 April 2025","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 April 2025","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 May 2025","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"50"}}