RESUMEN
COVID-19 is a novel virus that presents challenges due to a lack of consistent and in-depth research. The news of the COVID-19 spreads across the globe, resulting in a flood of posts on social media sites. Apart from health, social, and economic disturbances brought by the COVID-19 pandemic, another important consequence involves public mental health crises which is of greater concern. Data related to COVID-19 is a valuable asset for researchers in understanding people's feelings related to the pandemic. It is thus important to extract the early information evolving public sentiments on social platforms during the outbreak of COVID-19. The objective of this study is to look at people's perceptions of the COVID-19 pandemic who interact with each other and share tweets on the Twitter platform. COVIDSenti, a large-scale benchmark dataset comprising 90,000 COVID-19 tweets collected from February to March 2020, during the initial phases of the outbreak served as the foundation for our experiments. A pre-trained bidirectional encoder representations from transformers (BERT) model is fine-tuned and embeddings generated are combined with two long short-term memory networks to propose the residual encoder transformation network model. The proposed model is used for multiclass text classification on a large dataset labeled as positive, negative, and neutral. The experimental outcomes validate that: (1) the proposed model is the best performing model, with 98% accuracy and 96% F1-score; (2) It also outperforms conventional machine learning algorithms and different variants of BERT, and (3) the approach achieves better results as compared to state-of-the-art on different benchmark datasets.
RESUMEN
Depression has become one of the most widespread mental health disorders across the globe. Depression is a state of mind which affects how we think, feel, and act. The number of suicides caused by depression has been on the rise for the last several years. This issue needs to be addressed. Considering the rapid growth of various social media platforms and their effect on society and the psychological context of a being, it's becoming a platform for depressed people to convey feelings and emotions, and to study their behavior by mining their social activity through social media posts. The key objective of our study is to explore the possibility of predicting a user's mental condition by classifying the depressive from non-depressive ones using Twitter data. Using textual content of the user's tweet, semantic context in the textual narratives is analyzed by utilizing deep learning models. The proposed model, however, is a hybrid of two deep learning architectures, Convolutional Neural Network (CNN) and bi-directional Long Short-Term Memory (biLSTM) that after optimization obtains an accuracy of 94.28% on benchmark depression dataset containing tweets. CNN-biLSTM model is compared with Recurrent Neural Network (RNN) and CNN model and also with the baseline approaches. Experimental results based on various performance metrics indicate that our model helps to improve predictive performance. To examine the problem more deeply, statistical techniques and visualization approaches were used to show the profound difference between the linguistic representation of depressive and non-depressive content.