Word embeddings and deep learning for location prediction: tracking Coronavirus from British and American tweets

Abstract

With the propagation of the Coronavirus pandemic, current trends on determining its individual and societal impacts become increasingly important. Recent researches grant special attention to the Coronavirus social networks infodemic to study such impacts. For this aim, we think that applying a geolocation process is crucial before proceeding to the infodemic management. In fact, the spread of reported events and actualities on social networks makes the identification of infected areas or locations of the information owners more challenging especially at a state level. In this paper, we focus on linguistic features to encode regional variations from short and noisy texts such as tweets to track this disease. We pay particular attention to contextual information for a better encoding of these features. We refer to some neural network-based models to capture relationships between words according to their contexts. Being examples of these models, we evaluate some word embedding ones to determine the most effective features’ combination that has more spatial evidence. Then, we ensure a sequential modeling of words for a better understanding of contextual information using recurrent neural networks. Without defining restricted sets of local words in relation to the Coronavirus disease, our framework called DeepGeoloc demonstrates its ability to geolocate both tweets and twitterers. It also makes it possible to capture geosemantics of nonlocal words and to delimit the sparse use of local ones particularly in retweets and reported events. Compared to some baselines, DeepGeoloc achieved competitive results. It also proves its scalability to handle large amounts of data and to geolocate new tweets even those describing new topics in relation to this disease.

Sentiment-Based Spatiotemporal Prediction Framework for Pandemic Outbreaks Awareness Using Social Networks Data Classification

“…The highest accuracy was obtained using DT, at 85%. Using Deep Learning with word embedding, sentiment analysis, and featuring tweet content and tweet geolocation (longitude and latitude), the authors in [82] proposed DeepGeoloc with a max accuracy of 58.4%. Long-Short Term Memory (LSTM) was tested with different word embedding methods, such as Word2vec, FastText, and Char2vec.…”

Predictive Analysis of COVID-19 Symptoms in Social Networks through Machine Learning

“…One of the advantages of ReLU is that it will only deactivate the neurons if their result is less than 0. In this case, the negative values will be equal to 0 as disposed on Equation (5) in which the maximum value between 0 and the input value is returned, thus when the value is smaller than 0 it should return 0.…”

“…Since their advent, social networks have been widely used as a way for people to express emotions, feelings, opinions and information, as well as health concerns and symptoms, making these communication media potential sources for collecting and building a database of self-reported symptoms [4,5].…”

A Fine‐Grained Geolocalization Method for User Generated Short Text

“…Similarly, Borna et al [16] compared recurrent neural networks, convolutional neural networks and hierarchical attention networks for classification. Specifically, with the propagation of the Coronavirus pandemic, Hasni et al [17] focus on linguistic features to encode regional variations from short and noisy texts for location prediction.…”