NORMA eResearch @NCI Library

Combination of topic modelling and deep learning techniques for disaster trends prediction

Behera, Ankita (2019) Combination of topic modelling and deep learning techniques for disaster trends prediction. Masters thesis, Dublin, National College of Ireland.

[thumbnail of Master of Science]
PDF (Master of Science)
Download (1MB) | Preview


A natural disaster, even though its small, results in great human and environmental loss. If the disaster is predicted at the earlier stages, then it will be helpful for the people and the government for helping and coordinating with the rescue team. The media platform like Twitter is a valuable communication medium which allows the user to update about the condition and situation, which directly aware people in the affected area and helps rescue team to co-ordinate more effectively. This paper illustrates a recently developed approach which classifies various disaster and later predicts the trend from their severity level. This approach was previously applied in the field of mortality prediction and recommendation system. The framework consists of the integration of LDA for classification and LSTM (artificial recurrent neural network) for predicting the trends using the tweets. The proposed model is created considering the tweets and the weather data over a period. The model has predicted the accuracy of 80.5% with the neural network which is proved to better than any other machine learning techniques. This new combination of the latent topic information and the semantic information by the neural network shows great promise for improving the disaster management activities and forecasting the catastrophic trends.

Item Type: Thesis (Masters)
Subjects: Q Science > QA Mathematics > Electronic computers. Computer science
T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science
Q Science > QA Mathematics > Computer software
T Technology > T Technology (General) > Information Technology > Computer software
Divisions: School of Computing > Master of Science in Data Analytics
Depositing User: Caoimhe Ní Mhaicín
Date Deposited: 14 Oct 2019 09:33
Last Modified: 14 Oct 2019 09:33

Actions (login required)

View Item View Item