TY  - JOUR
PY  - 2021//
TI  - Twitter for disaster relief through sentiment analysis for COVID-19 and natural hazard crises
JO  - International journal of disaster risk reduction
A1  - Behl, Shivam
A1  - Rao, Aman
A1  - Aggarwal, Sahil
A1  - Chadha, Sakshi
A1  - Pannu, H. S.
SP  - e102101
EP  - e102101
VL  - 55
IS  - 
N2  - In emergencies and disasters, large numbers of people require basic needs and medical attention. In such situations, online social media comes as a possible solution to aid the current disaster management methods. In this paper, supervised learning approaches are compared for the multi-class classification of Twitter data. A careful setting of Multilayer Perceptron (MLP) network layers and the optimizer has shown promising results for classification of tweets into three categories i.e. 'resource needs', 'resource availability', and 'others' being neutral and of no useful information. Public data of Nepal Earthquake (2015) and Italy Earthquake (2016) have been used for training and validation of the models, and original COVID-19 data is acquired, annotated, and used for testing. Detailed data analysis of tweets collected during different disasters has also been incorporated in the paper. The proposed model has been able to achieve 83% classification accuracy on the original COVID-19 dataset. Local Interpretable Model-Agnostic Explanations (LIME) is used to explain the behavior and shortcomings model on COVID-19 data. This paper provides a simple choice for real-world applications and a good starting point for future research.<p />  <p>Language: en</p>
LA  - en
SN  - 2212-4209
UR  - http://dx.doi.org/10.1016/j.ijdrr.2021.102101
ID  - ref1
ER  -