Comparison of different machine learning algorithms to classify whether or not a tweet is about a natural disaster: a simulation-based approach

Subrata Dutta, Manish Kumar, Arindam Giri, Ravi Bhushan Thakur, Sarmistha Neogy, Keshav Dahal

Research output: Chapter in Book/Report/Conference proceedingChapterpeer-review

1 Citation (Scopus)

Abstract

In this digital world, social media is full of information that reveals current situations as well as trends in society over a particular time. This information can be used to handle real life problem, which occur due to changes in natural environments. To deal with an emergency situation as well as to spread awareness over that situation, accurate and timely information plays an important role. We can utilize the power of artificial intelligence in combination with social media information for betterment of mankind. In this chapter, we use various machine learning algorithms to classify a tweet, determine whether or not it is about natural disaster, and compare the results of classification algorithms in order to identify the best one in analyzing Twitter data. Logistic regression provides the most accurate result (~79%). This chapter discusses the role of social media (presently, Twitter) in natural disaster or emergency situations along with current research works and challenges faced by researchers in this field.

Original languageEnglish
Title of host publicationRecommender Systems
Subtitle of host publicationA Multi-Disciplinary Approach
EditorsMonideepa Roy, Pushpendu Kar, Sujoy Datta
PublisherCRC Press
Chapter1
Number of pages16
ISBN (Electronic)9781003319122
ISBN (Print)9781032333212
DOIs
Publication statusPublished - 19 Jun 2023

Publication series

NameIntelligent Systems
PublisherCRC Press

Fingerprint

Dive into the research topics of 'Comparison of different machine learning algorithms to classify whether or not a tweet is about a natural disaster: a simulation-based approach'. Together they form a unique fingerprint.

Cite this