Home / Current Issue / Paper 1704031
Disaster Tweets Classification
Subject area: Science,Engineering and Technology · Area of research: Social Media , Machine Learning
Abstract
Social media's enormous data output offers a singular opportunity for disaster research. As a top social media network, Twitter produces more than 500 million Tweets daily. Twitter is increasingly used by authorities to track disaster situations and develop quick rescue plans due to its real-time capability. Building a precise predictive model to recognize disaster Tweets, which might not have enough context due to the length restriction, is difficult. Determining the optimal algorithm to drive a recommendation engine that will aid in real-time crisis occurrences for the purpose of delivering relief to the affected, gathering news, etc. will therefore be the goal of this project.
How to cite this paper
@article{1704031,
author = {Gaurav Kanojia, Aditya Rastogi},
title = {Disaster Tweets Classification},
journal = {Iconic Research And Engineering Journals},
year = {2023},
volume = {6},
number = {7},
pages = {295-298},
issn = {2456-8880},
url = {https://www.irejournals.com/formatedpaper/1704031.pdf},
abstract = {Social media's enormous data output offers a singular opportunity for disaster research. As a top social media network, Twitter produces more than 500 million Tweets daily. Twitter is increasingly used by authorities to track disaster situations and develop quick rescue plans due to its real-time capability. Building a precise predictive model to recognize disaster Tweets, which might not have enough context due to the length restriction, is difficult. Determining the optimal algorithm to drive a recommendation engine that will aid in real-time crisis occurrences for the purpose of delivering relief to the affected, gathering news, etc. will therefore be the goal of this project.},
month = {January},
}