%0 Journal Article %1 noauthororeditor %A |, Geetha M | Maria Michael Visuwasam L | Sripaad Srinivasan | Veera Raghavan G | Venkatraman K %D 2023 %J CENTRAL ASIAN JOURNAL OF MEDICAL AND NATURAL SCIENCE %K Analysis, Big Data Language Learning, Machine Natural ProcessingData Sentiment %N 1 %P 72-96 %T Natural Language Processing Based Disaster Management Framework %U https://cajmns.centralasianstudies.org/index.php/CAJMNS/article/view/1294/1260 %V 4 %X In times of crisis, more and more people are turning to social media to reach out to others and ask for assistance. Such requests must be mined from the large data pool in order to provide prompt assistance during emergency circumstances. How well relief efforts and disaster recovery go depends on how people feel during and after a crisis. In order to aid in the speedy recovery of the afflicted area, we want to investigate and comprehend the underlying tendencies in sentiment to disasters and geographically connected sentiment. The proposed DRM Framework (Disaster Recovery and Management Framework) takes in information about disasters from various sources, organises it according to the needs of the affected people, and uses a custom-built Natural Language Processing (NLP) model to categorise the severity level for a given geographical location. A machine learning algorithm is used to categorise the disaster data and analyse public opinion. The suggested methodology has important implications for disaster response and recovery, including the real-time categorization and classification of Big Data. Using the results of this investigation, first responders and rescue workers will be better prepared to deal with the dynamic nature of crisis situations.

@article{noauthororeditor, abstract = {In times of crisis, more and more people are turning to social media to reach out to others and ask for assistance. Such requests must be mined from the large data pool in order to provide prompt assistance during emergency circumstances. How well relief efforts and disaster recovery go depends on how people feel during and after a crisis. In order to aid in the speedy recovery of the afflicted area, we want to investigate and comprehend the underlying tendencies in sentiment to disasters and geographically connected sentiment. The proposed DRM Framework (Disaster Recovery and Management Framework) takes in information about disasters from various sources, organises it according to the needs of the affected people, and uses a custom-built Natural Language Processing (NLP) model to categorise the severity level for a given geographical location. A machine learning algorithm is used to categorise the disaster data and analyse public opinion. The suggested methodology has important implications for disaster response and recovery, including the real-time categorization and classification of Big Data. Using the results of this investigation, first responders and rescue workers will be better prepared to deal with the dynamic nature of crisis situations.}, added-at = {2023-08-22T13:52:15.000+0200}, author = {|, Geetha M | Maria Michael Visuwasam L | Sripaad Srinivasan | Veera Raghavan G | Venkatraman K}, biburl = {https://www.bibsonomy.org/bibtex/205087281a6e6eb4c7e298168c988a10d/centralasian_20}, interhash = {8b4cbd26172d210528e9f6eed567a92c}, intrahash = {05087281a6e6eb4c7e298168c988a10d}, issn = {2660-4159}, journal = {CENTRAL ASIAN JOURNAL OF MEDICAL AND NATURAL SCIENCE}, keywords = {Analysis, Big Data Language Learning, Machine Natural ProcessingData Sentiment}, language = {english}, month = jan, number = 1, pages = {72-96}, timestamp = {2023-08-22T13:52:15.000+0200}, title = {Natural Language Processing Based Disaster Management Framework}, url = {https://cajmns.centralasianstudies.org/index.php/CAJMNS/article/view/1294/1260}, volume = 4, year = 2023 }