Open Access

ARTICLE

Evaluating Public Sentiments during Uttarakhand Flood: An Artificial Intelligence Techniques

by Stephen Afrifa^1,2,*, Vijayakumar Varadarajan^3,4,5,*, Peter Appiahene², Tao Zhang¹, Richmond Afrifa⁶

1 School of Electrical and Information Engineering, Tianjin University, Tianjin, 300072, China
2 Department of Information Technology and Decision Sciences, University of Energy and Natural Resources, Sunyani, 00233, Ghana
3 International Divisions, Ajeenkya D.Y. Patil University, Pune, 412105, India
4 Business School, La Trobe University, Melbourne, Victoria, 3086, Australia
5 Research Division, Swiss School of Business and Management, Geneva, 1213, Switzerland
6 Department of Social Science and Geography, Aprade Senior High Technical School, Koforidua, 03225, Ghana

* Corresponding Authors: Stephen Afrifa. Email: ; Vijayakumar Varadarajan. Email:

Computer Systems Science and Engineering 2024, 48(6), 1625-1639. https://doi.org/10.32604/csse.2024.055084

Received 16 June 2024; Accepted 05 September 2024; Issue published 22 November 2024

Abstract

Users of social networks can readily express their thoughts on websites like Twitter (now X), Facebook, and Instagram. The volume of textual data flowing from users has greatly increased with the advent of social media in comparison to traditional media. For instance, using natural language processing (NLP) methods, social media can be leveraged to obtain crucial information on the present situation during disasters. In this work, tweets on the Uttarakhand flash flood are analyzed using a hybrid NLP model. This investigation employed sentiment analysis (SA) to determine the people’s expressed negative attitudes regarding the disaster. We apply a machine learning algorithm and evaluate the performance using the standard metrics, namely root mean square error (RMSE), mean absolute error (MAE), and mean absolute percentage error (MAPE). Our random forest (RF) classifier outperforms comparable works with an accuracy of 98.10%. In order to gain a competitive edge, the study shows how Twitter (now X) data and machine learning (ML) techniques can analyze public discourse and sentiments regarding disasters. It does this by comparing positive and negative comments in order to develop strategies to deal with public sentiments on disasters.

---

Keywords

---