Application of named entity recognition on tweets during earthquake disaster: a deep learning-based approach

Twitter is an intensely utilized platform for disaster events and emergencies. Therefore, Twitter is an important resource for providing the essential information. Named entity recognition (NER), which is the process of determining the elementary units in a text and classifying them with pre-defined categories, plays a significant role to extract essential and usefulness information. However, NER is a challenging task due to the utilized informal text in the Twitter platform such as grammatical errors and nonstandard abbreviations. In this paper, recurrent neural network (RNN)-based approaches considering diversity of activation functions and optimization functions with NER tools are utilized to extract named entities such as organization, person, and location from the tweets. Inputs for RNN models are provided via two different NER tools which are natural language toolkit (NLTK) and general architecture for text engineering (Gate). Then, pre-labeled data are trained via GloVe word embedding technique, and RNN model variants such as LSTM, BLSTM, and GRU are demonstrated. Therefore, outperforming models among RNN variants are presented for predicting named entities. Yellowbrick interpreter is used for evaluation of the proposed method and Wilcoxon signed-rank test are applied on results of two different data sets to demonstrate consistency of the proposed method. In addition, comparison is made with existing machine learning methods. The experiments by utilizing the Nepal earthquake Twitter data set show that the RNN-based approaches achieve good results in finding named entities. In emergencies, the results of this paper can help in reducing the efforts of event location detection and provide better disaster management.