NLPRL at WNUT-2020 Task 2: ELMo-based System for Identification of COVID-19 Tweets

The Coronavirus pandemic has been a dominating news on social media for the last many months. Efforts are being made to reduce its spread and reduce the casualties as well as new infections. For this purpose, the information about the infected people and their related symptoms, as available on social media, such as Twitter, can help in prevention and taking precautions. This is an example of using noisy text processing for disaster management. This paper discusses the NLPRL results in Shared Task-2 of WNUT-2020 workshop. We have considered this problem as a binary classification problem and have used a pre-trained ELMo embedding with GRU units. This approach helps classify the tweets with accuracy as 80.85% and 78.54% as F1-score on the provided test dataset. The experimental code is available online.

[1]  Yung-Hsiang Chen,et al.  Multiple-Input Deep Convolutional Neural Network Model for COVID-19 Forecasting in China , 2020, medRxiv.

[2]  Neeraj Gupta,et al.  Prediction for the spread of COVID-19 in India and effectiveness of preventive measures , 2020, Science of The Total Environment.

[3]  Vinay Kumar Reddy Chimmula,et al.  Time series forecasting of COVID-19 transmission in Canada using LSTM networks , 2020, Chaos, Solitons & Fractals.

[4]  Akash Dutt Dubey,et al.  Twitter Sentiment Analysis during COVID19 Outbreak , 2020, SSRN Electronic Journal.

[5]  Roland Vollgraf,et al.  Contextual String Embeddings for Sequence Labeling , 2018, COLING.

[6]  G. Chowell,et al.  Transmission potential and severity of COVID-19 in South Korea , 2020, International Journal of Infectious Diseases.

[7]  L. Yang,et al.  Preliminary estimation of the basic reproduction number of novel coronavirus (2019-nCoV) in China, from 2019 to 2020: A data-driven analysis in the early phase of the outbreak , 2020, International Journal of Infectious Diseases.

[8]  Luke S. Zettlemoyer,et al.  Deep Contextualized Word Representations , 2018, NAACL.

[9]  Xiao Xiang Zhu,et al.  Cross-language sentiment analysis of European Twitter messages during the COVID-19 pandemic , 2020, NLPCOVID19.

[10]  Yoshua Bengio,et al.  On the Properties of Neural Machine Translation: Encoder–Decoder Approaches , 2014, SSST@EMNLP.

[11]  Dat Quoc Nguyen,et al.  WNUT-2020 Task 2: Identification of Informative COVID-19 English Tweets , 2020, WNUT.

[12]  Qing Zhu,et al.  COVID-19 Sensing: Negative Sentiment Analysis on Social Media in China via BERT Model , 2020, IEEE Access.

[13]  Keyuan Jiang,et al.  Identifying tweets of personal health experience through word embedding and LSTM neural network , 2018, BMC Bioinformatics.

[14]  Marta Giovanetti,et al.  Application of the ARIMA model on the COVID-2019 epidemic dataset , 2020, Data in Brief.

[15]  Kyujin Jung,et al.  Social Media Use during Japan's 2011 Earthquake: How Twitter Transforms the Locus of Crisis Communication , 2013 .

[16]  B. K. Panigrahi,et al.  Prediction and analysis of COVID-19 positive cases using deep learning models: A descriptive case study of India , 2020, Chaos, Solitons & Fractals.

[17]  Marcel Salathé,et al.  COVID-Twitter-BERT: A natural language processing model to analyse COVID-19 content on Twitter , 2020, Frontiers in Artificial Intelligence.

[18]  Benjamin Schrauwen,et al.  Training and Analysing Deep Recurrent Neural Networks , 2013, NIPS.

[19]  Samarjit Kar,et al.  Neural network based country wise risk prediction of COVID-19 , 2020, Applied Sciences.

[20]  Roland Vollgraf,et al.  FLAIR: An Easy-to-Use Framework for State-of-the-Art NLP , 2019, NAACL.

[21]  Samir Kumar Bandyopadhyay,et al.  Machine Learning Approach for Confirmation of COVID-19 Cases: Positive, Negative, Death and Release , 2020, medRxiv.