Machine Learning Models for Mining Social Media Data for Effective Natural Disaster Assessment DOI Creative Commons
Prahlada Varada Mittal,

Sejal Karki,

S. V. Parasher

et al.

Research Square (Research Square), Journal Year: 2023, Volume and Issue: unknown

Published: Dec. 18, 2023

Abstract Satellite technology has emerged as a key tool for effective management and assessment of natural disasters. However, the challenge accurately estimating impacted populations assessing building damage, often obscured from aerial views, persists. To address this, integration imagery textual data social networks offers promising solution. This study employs Twitter Flickr datasets, using SVM, CNN, XGBoost, Logistic Regression, Gradient Boost to extract insights. The sentiment analysis component categorizes disaster-affected individuals' emotions panic, neutral, or non-panic. Regression model excels in text classification, boasting an impressive 88.99% accuracy on test dataset 83.45% training. framework introduces Aid model, which gives us 83.16% classification tweets based aid sought by people through tweets. Image achieving 83.29% comprehend disaster impact visually. Given real-time media responses, system assists government organisations promptly, prioritising assistance. It serves dependable resource, enabling efficient responses tailored affected communities. Thus, this approach holds potential significantly enhance relief efficacy.

Language: Английский

Human cognitive limitations and emotions: The emergence of social complexity DOI
Pedro C. Marijuán, Jorge Navarro

Biosystems, Journal Year: 2025, Volume and Issue: 251, P. 105454 - 105454

Published: March 11, 2025

Language: Английский

Citations

0
A systematic review of social media-based sentiment analysis in disaster risk management DOI Creative Commons

Bilal Ilyas,

Ayyoob Sharifi

International Journal of Disaster Risk Reduction, Journal Year: 2025, Volume and Issue: unknown, P. 105487 - 105487

Published: April 1, 2025

Language: Английский

Citations

0
Comparative Analysis of Classification Methods in Sentiment Analysis: The Impact of Feature Selection and Ensemble Techniques Optimization DOI Open Access
Sarjon Defit, Agus Perdana Windarto,

Putrama Alkhairi

et al.

Telematika, Journal Year: 2024, Volume and Issue: 17(1), P. 52 - 67

Published: Feb. 16, 2024

Optimizing classification methods (forward selection, backward elimination, and optimized selection) ensemble techniques (AdaBoost Bagging) are essential for accurate sentiment analysis, particularly in political contexts on social media. This research compares advanced models with standard ones (Decision Tree, Random Naive Bayes, Forest, K- NN, Neural Network, Generalized Linear Model), analyzing 1,200 tweets from December 10-11, 2023, focusing "Indonesia" "capres." It encompasses 490 positive, 355 negative, 353 neutral sentiments, reflecting diverse opinions presidential candidates issues. The enhanced model achieves 96.37% accuracy, the selection reaching 100% accuracy negative sentiments. study suggests further exploration of hybrid feature improved classifiers high-stakes analysis. With forward method, Bayes stands out classifying sentiments while maintaining high overall (96.37%).

Language: Английский

Citations

2
Mood and emotion assessment for risk reduction of pandemic spread through passenger air transport: a DSS applied to the COVID‐19 in the case of Spain DOI Creative Commons
Juan Aguarón, Alfredo Altuzarra Casas,

R. Aznar

et al.

International Transactions in Operational Research, Journal Year: 2024, Volume and Issue: unknown

Published: Nov. 14, 2024

Abstract This paper presents a decision support system (DSS) for sentiment analysis of Spanish texts based on lexicons. The information provided by this DSS, named Sentiment Analysis‐DSS (SSA‐DSS), is employed to assess the social impacts considered in an external software module (RRPS‐PAT) centered risk reduction pandemic spread through passenger air transport. RRPS‐PAT complex multiobjective optimization simultaneously addressing different conflicting objectives, including epidemiological, economic, and aspects. allows more effective realistic decisions be made. specificity novelty problem suggest use lexicon‐based approaches because there no prior about train machine learning–based approaches. SSA‐DSS covers entire process from incorporation texts, particularly tweets, analyzed, application preprocessing cleaning tools, selection lexicons (general, context, emoji lexicons) used their possible modification, visualization results exportation other tools. contemplates, apart module, connection with network tool (Gephi) that complements identification leaders. usefulness functionalities are illustrated means example related evolution societal mood Spain during COVID‐19 pandemic.

Language: Английский

Citations

2
Assessment of text-generated supply chain risks considering news and social media during disruptive events DOI Creative Commons
Soumik Nafis Sadeek, Shinya Hanaoka

Social Network Analysis and Mining, Journal Year: 2023, Volume and Issue: 13(1)

Published: July 8, 2023

Abstract Information flow is an important task in a supply chain network. Disruptive events often impede this due to confounding factors, which may not be identified immediately. The objective of study assess risks by detecting significant risks, examining risk variations across different time phases and establishing sentiment relationships utilizing textual data. We examined two disruptive events—coronavirus disease 2019 (Omicron phase) the Ukraine–Russia war—between November 2021 April 2022. Data sources included news media Twitter. Latent Dirichlet Allocation algorithm was applied data extract potential text-generated form “topics.” A proportion these were analyzed their time-varying nature. Natural language processing-based analysis infer coming from using ordered probit model. results identify various unnoticed for example: logistics tension, resiliency, ripple effect, regional chain, etc. that adversely affect operations if considered. outcomes also indicate are capable capturing before actually occur. further suggest text could valuable strategic decision making improving visibility.

Language: Английский

Citations

6
Sentiment and Context-Aware Recurrent Convolutional Neural Network for Sentiment Analysis DOI

Umasree Mariappan,

D. Balakrishnan,

S.J. Subhashini

et al.

Published: Aug. 25, 2023

Sentiment analysis is a Natural Language Processing (NLP) task that involves using machine learning techniques, particularly deep learning, to determine the sentiment or emotion expressed in piece of text. The goal understand whether text expresses positive, negative, neutral towards particular subject, product, service, topic. A technique called and Context-Aware Hybrid Deep Neural Network (SCA-HDNN) was proposed for analysis. In SCA-HDNN, Convolutional (CNN) used classification. However, CNNs require fixed-sized inputs, which can be limitation when dealing with sequences different lengths. So this paper, Recurrent CNN (RCNN) introduced incorporation recurrent connections each convolutional layer RCNN enables handling variable-length sequences. RCNNs more computationally efficient than CNN. combination RNNs allows parallelization shared computations across time steps, speed up training inference This method named as SCA-RCNN. results from experiment demonstrate suggested SCA-RCNN achieves high levels accuracy, precision, recall

Language: Английский

Citations

4
A Method to Classify Texts Based on Sentiment Analysis and Machine Learning DOI Open Access

Claudia Corona López,

Jesus Urias Piña,

Rafael Lahoz-Beltrá

et al.

Published: March 5, 2024

In this paper we describe a method which combines sentiment analysis with machine learning techniques and/or multivariate statistical analysis. By applying methodology it is possible to classify collection of texts into two or more groups clusters. On the basis number previously defined clusters, novelty outlined approach use results as input model Once classifier has been obtained, can assign given text one pre-established The clusters represent different time periods, classes transcribed from conversations, etc. illustrated through an example taken studies in have applied methodology. studies, was used press news volcanic eruption, while other study conversations recorded between chatbot kinds speakers (humans chatbots). This last seminal work introduced

Language: Английский

Citations

1
The 2021 La Palma eruption: social dilemmas resulting from life close to an active volcano DOI Creative Commons
Valentin R. Troll, Meritxell Aulinas, Juan Carlos Carracedo

et al.

Geology Today, Journal Year: 2024, Volume and Issue: 40(3), P. 96 - 111

Published: May 1, 2024

Damage and destruction caused by the 2021 eruption of Tajogaite volcano on La Palma was unprecedented relative to other historical eruptions last century (1909, 1949, 1971, 2011) in Canary Islands. The devastation not a result magnitude, which only marginally larger than events, but instead an increasing vulnerability due population growth rural land use slopes volcanically active Cumbre Vieja Ridge. Since future along are inevitable, it is imperative that actions taken ensure safety island's growing population. While civil protection emergency services managed avert loss life from direct volcanic impacts 2021, property for many people affected area remains grave issue requires targeted measures safeguard against human suffering similar events.

Language: Английский

Citations

1
The 2021 La Palma eruption; social dilemmas resulting from living close to an active volcano DOI Creative Commons
Valentin R. Troll, Meritxell Aulinas, Juan Carlos Carracedo

et al.

EarthArXiv (California Digital Library), Journal Year: 2023, Volume and Issue: unknown

Published: Sept. 20, 2023

Damage and destruction caused by the 2021 eruption of Tajogaite volcano on La Palma was unprecedented relative to other historical eruptions last century (1909, 1949, 1971, 2011) in Canary Islands. The devastation not a result magnitude, which only marginally larger than events, but instead increasing vulnerability due population growth rural land use slopes volcanically active Cumbre Vieja Ridge. Since future along are inevitable, it is imperative that actions taken ensure safety island’s growing population. While civil protection emergency services managed avert loss life from direct volcanic impacts 2021, property for many people affected area remains grave issue requires targeted measures safeguard against human suffering similar events.

Language: Английский

Citations

3
The Analysis of Communication Strategy of Disabled Sports Information Based on Deep Learning and the Internet of Things DOI Creative Commons

Wanglong Wang,

Qingwen Liu, Chuan Shu

et al.

IEEE Access, Journal Year: 2024, Volume and Issue: 12, P. 45976 - 45985

Published: Jan. 1, 2024

Language: Английский

Citations

0