Informative Tweet Classification of the Earthquake Disaster Situation In Indonesia

Gata, Windu; Amsury, Fachri; Wardhani, Nia Kusuma; Sugiyarto, Ipin; Sulistyowati, Daning Nur; Saputra, Irwansyah

doi:10.1109/icced46541.2019.9161135

Cited by 9 publications

(3 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Other work supports that social media is an important venue for big data and AI analysis regarding the disaster lifecycle-and that more such research can improve real-time response and preparedness. [52][53][54][55][56][57][58][59] Food intake has long been associated with mental health and well-being, [60][61][62][63] so it is unsurprising that the third most popular tweet category involved these themes. During the COVID-19 pandemic, other studies have shown that lock-down periods were associated vicious cycles of https://doi.org/10.1017/dmp.2022.207 Published online by Cambridge University Press increased food insecurity and worse mental health outcomes-like depression and anxiety disorder-and in turn, these disorders lead to more unhealthy eating.…”

Section: Discussionmentioning

confidence: 99%

Enhancing Artificial Intelligence for Twitter-based Public Discourse on Food Security During the COVID-19 Pandemic

Martin¹,

Poirier²,

Rosenblum

et al. 2022

Disaster med. public health prep.

View full text Add to dashboard Cite

Objective: Food security during public health emergencies relies on situational awareness of needs and resources. Artificial intelligence (AI) has revolutionized situational awareness during crises, allowing the allocation of resources to needs through machine learning algorithms. Limited research exists monitoring Twitter for changes in the food security-related public discourse during the COVID-19 pandemic. We aim to address that gap with AI by classifying food security topics on Twitter and showing topic frequency per day. Methods: Tweets were scraped from Twitter from January 2020 through December 2021 using food security keywords. Latent Dirichlet Allocation (LDA) topic modeling was performed, followed by time-series analyses on topic frequency per day. Results: 237,107 tweets were scraped and classified into topics, including food needs and resources, emergency preparedness and response, and mental/physical health. After the WHO’s pandemic declaration, there were relative increases in topic density per day regarding food pantries, food banks, economic and food security crises, essential services, and emergency preparedness advice. Threats to food security in Tigray emerged in 2021. Conclusions: AI is a powerful yet underused tool to monitor food insecurity on social media. Machine learning tools to improve emergency response should be prioritized, along with measurement of impact. Further food insecurity word patterns testing, as generated by this research, with supervised machine learning models can accelerate the uptake of these tools by policymakers and aid organizations.

show abstract

Section: Discussionmentioning

confidence: 99%

Enhancing Artificial Intelligence for Twitter-based Public Discourse on Food Security During the COVID-19 Pandemic

Martin¹,

Poirier²,

Rosenblum

et al. 2022

Disaster med. public health prep.

View full text Add to dashboard Cite

show abstract

“…The following is a framework that is carried out based on the steps and procedures of this research process Figure 1 explains that the research model carried out is the classification of tweets containing support for implementing the Formula E event in Indonesia, precisely in Jakarta. The text mining technique and the Support Vector Machine (SVM) and Naïve Bayes methods are used by applying the SMOTE technique to balance the data (Gata et al, 2019).…”

Section: Methodsmentioning

confidence: 99%

Comparison of Classification Algorithms for Analysis Sentiment of Formula E Implementation in Indonesia

2022

Self Cite

View full text Add to dashboard Cite

The Formula E racing series has become one of the world's most prestigious competitions. In 2022, Indonesia hosted the famous Formula E race. The event possesses the potential for economic benefits for Indonesia worth 78 million euros through the arrival of 35,000 spectators. Indonesians are enthusiastic about Formula E since it allows their nation to encourage tourists and gain international prominence. However, some people do not support this event. Since they regard that amid the COVID-19 pandemic, it is preferable for the government to focus on people affected by the pandemic rather than support a Formula E event. This study compares the Support Vector Machine and Naive Bayes algorithms in classifying public opinion in the Formula E race. This study gets its information from user comments on social media platforms, especially Twitter. The stages start with text preprocessing and include cleaning, case folding, tokenization, filtering, and stemming. Proceed with weighting using the TF-IDF approach. Data testing uses a confusion matrix to evaluate the classification results by testing accuracy, precision, and recall. Categorizing public opinion using the SVM algorithm has an accuracy of 82 percent, a precision of 97.86 percent, and a recall of 77.90 percent. On the other hand, the accuracy of the Naive Bayes technique is more limited, at 87.54 percent. Society's opinion on Twitter shows positive sentiment towards implementing Formula E.

show abstract

“…It enables people to post real-time and on-topic information about their status, reports on damage to infrastructure, and information about injured people or loss of life [6][7][8]. Disaster crisis-related tweets have proven particularly effective in many human-made or naturally occurring crises such as oods [9], earthquakes [10], nuclear disasters [11] and wild res [12]. However, while tweets provide important information, they often contain a signi cant amount of unrelated or irrelevant information.…”

Section: Introductionmentioning

confidence: 99%

Effective Tweets Classification for Disaster Crisis based on Ensemble of Classifiers

Eke,

Mulenga,

Phiri

et al. 2023

Preprint

View full text Add to dashboard Cite

In the field of disaster crisis management, the utilization of social media platforms has gained significant recognition. It helps in disseminating and gathering information during disasters, offering real-time updates on events, infrastructure damage reports, and casualty information. However, the information comes with a substantial amount of irrelevant content. Some researchers have utilized machine learning classifiers for classification, which has become ineffective. Thus, this study proposes an ensemble-based approach to disaster tweet classification, using a wide array of linguistic and word embedding features, Additionally, we investigate various supervised learning algorithms and ensemble classifiers for resolving this issue. Our findings reveal that the ensemble feature sets, specifically, the fusion of TF-IDF and word embeddings, when coupled with Bagging, achieved a classification accuracy of 98.92%. This research highlights the potential of leveraging machine learning and ensemble techniques on disaster tweet classification, providing insights for improving real-time disaster response efforts.

show abstract

Informative Tweet Classification of the Earthquake Disaster Situation In Indonesia

Cited by 9 publications

References 19 publications

Enhancing Artificial Intelligence for Twitter-based Public Discourse on Food Security During the COVID-19 Pandemic

Enhancing Artificial Intelligence for Twitter-based Public Discourse on Food Security During the COVID-19 Pandemic

Comparison of Classification Algorithms for Analysis Sentiment of Formula E Implementation in Indonesia

Effective Tweets Classification for Disaster Crisis based on Ensemble of Classifiers

Contact Info

Product

Resources

About