A stacked convolutional neural network for detecting the resource tweets during a disaster

Abstract

Social media platform like Twitter is one of the primary sources for sharing real-time information at the time of events such as disasters, political events, etc. Detecting the resource tweets during a disaster is an essential task because tweets contain different types of information such as infrastructure damage, resources, opinions and sympathies of disaster events, etc. Tweets are posted related to Need and Availability of Resources (NAR) by humanitarian organizations and victims. Hence, reliable methodologies are required for detecting the NAR tweets during a disaster. The existing works don’t focus well on NAR tweets detection and also had poor performance. Hence, this paper focus on detection of NAR tweets during a disaster. Existing works often use features and appropriate machine learning algorithms on several Natural Language Processing (NLP) tasks. Recently, there is a wide use of Convolutional Neural Networks (CNN) in text classification problems. However, it requires a large amount of manual labeled data. There is no such large labeled data is available for NAR tweets during a disaster. To overcome this problem, stacking of Convolutional Neural Networks with traditional feature based classifiers is proposed for detecting the NAR tweets. In our approach, we propose several informative features such as aid, need, food, packets, earthquake, etc. are used in the classifier and CNN. The learned features (output of CNN and classifier with informative features) are utilized in another classifier (meta-classifier) for detection of NAR tweets. The classifiers such as SVM, KNN, Decision tree, and Naive Bayes are used in the proposed model. From the experiments, we found that the usage of KNN (base classifier) and SVM (meta classifier) with the combination of CNN in the proposed model outperform the other algorithms. This paper uses 2015 and 2016 Nepal and Italy earthquake datasets for experimentation. The experimental results proved that the proposed model achieves the best accuracy compared to baseline methods.

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

“…While this progress on food security is valuable, future work can be improved upon by taking guidance from other fields that have made progress on identifying needs and resources on microblogs, even though they are not explicitly focused on food. [42][43][44][45][46][47][48] Recent studies have improved performance of classifying needs and resources through the use of key terms mapped to crisis scenarios and the general detection of needs and resources. 49 This includes crisis-related lexicons, e.g., EMTerms 50 and CrisisLex 51 , that contain over 7,000 terms used in Twitter to describe various crises.…”

CAMM: Cross-Attention Multimodal Classification of Disaster-Related Tweets

“…Similarly, Purohit et al [9] attempted to prioritize the requests made by the affected people to be serviced by the emergency responders. In a recent study by Madichetty et al [41], authors filtered 'Need and Availability Resources (NAR)' tweets from the Nepal and Italy earthquakes that happened in 2015 and 2016, respectively, using a stacked architecture of CNN with traditional classifiers. Their experiments on various classifiers confirm that K-Nearest-Neighbor as the base classifier, Support Vector Machine as the meta classifier, and CNN give the best results.…”

COVID-19 outbreak: An ensemble pre-trained deep learning model for detecting informative tweets

“…Madichetty has focused informative tweets identification of natural disasters, and Sridevi (2020c) [21] are examined the model using SVM (meta classifier) and KNN (base classifier) with the combination of CNN outperforms the other algorithms The Deep Learning models (CNN, LSTM, BLSTM, and BLSTM attention) are used to identify situational information during a disaster in Hindi language tweets, besides English language tweets. Deep learning model results outperform existing classic disaster-set approaches, such as Hagupit cyclone, Hyderabad bomb blast, Sandhy shooting, Harda rail accident, and Earthquake.…”