Exploring Social Media for Early Detection of Depression in COVID-19 Patients

The COVID-19 pandemic has caused substantial damage to global health. Even though three years have passed, the world continues to struggle with the virus. Concerns are growing about the impact of COVID-19 on the mental health of infected individuals, who are more likely to experience depression, which can have long-lasting consequences for both the affected individuals and the world. Detection and intervention at an early stage can reduce the risk of depression in COVID-19 patients. In this paper, we investigated the relationship between COVID-19 infection and depression through social media analysis. Firstly, we managed a dataset of COVID-19 patients that contains information about their social media activity both before and after infection. Secondly, We conducted an extensive analysis of this dataset to investigate the characteristic of COVID-19 patients with a higher risk of depression. Thirdly, we proposed a deep neural network for early prediction of depression risk. This model considers daily mood swings as a psychiatric signal and incorporates textual and emotional characteristics via knowledge distillation. Experimental results demonstrate that our proposed framework outperforms baselines in detecting depression risk, with an AUROC of 0.9317 and an AUPRC of 0.8116. Our model has the potential to enable public health organizations to initiate prompt intervention with high-risk patients. © 2023 ACM.

Covid-19 Vaccination Stance Detection Using Natural Language Processing and Machine-Learning Algorithms

The coronavirus outbreak has resulted in unprecedented measures, forcing authorities to make decisions related to establishing lockdowns in areas most affected by the pandemic. Social Media have supported people during this difficult time. On November 9, 2020, when the first vaccine with an efficacy rate over 90% was announced, social media reacted and people around the world began to express their feelings about this vaccination. This paper aims to analyze the dynamics of opinion on COVID-19 vaccination, in which the civil society is highly manifested in the vaccination process. We compared classical machine learning algorithms to select the best performing classifier. 4,392 tweets were collected and analyzed. The proposed approach can help governments create and evaluate appropriate communication tools to provide clear and relevant information to the general public, increasing public confidence in vaccination campaigns. © 2022 Copyright for this paper by its authors.

Fake News Detection Using Transformer and Ensemble Learning Models

On social media, misinformation can spread quickly, posing serious problems. Understanding the content and sensitive nature of fake news and misinformation is critical to prevent the damage caused by them. To this end, the characteristics of information must first be discerned. In this paper, we propose a transformer-based hybrid ensemble model to detect misinformation on the Internet. First, false and true news on Covid-19 were analyzed, and various text classification tasks were performed to understand their content. The results were utilized in the proposed hybrid ensemble learning model. Our analysis revealed promising results, establishing the capability of the proposed system to detect misinformation on social media. The final model exhibited an excellent F1 score (0.98) and accuracy (0.97). The AUC (Area Under The Curve) score was also high at 0.98, and the ROC (Receiver Operating Characteristics) curve revealed that the true-positive rate of the data was close to one in this model. Thus, the proposed hybrid model was demonstrated to be successful in recognizing false information online. © 2022 IEEE.

Analyzing COVID-Related Social Discourse on Twitter using Emotion, Sentiment, Political Bias, Stance, Veracity and Conspiracy Theories

Online misinformation has become a major concern in recent years, and it has been further emphasized during the COVID-19 pandemic. Social media platforms, such as Twitter, can be serious vectors of misinformation online. In order to better understand the spread of these fake-news, lies, deceptions, and rumours, we analyze the correlations between the following textual features in tweets: emotion, sentiment, political bias, stance, veracity and conspiracy theories. We train several transformer-based classifiers from multiple datasets to detect these textual features and identify potential correlations using conditional distributions of the labels. Our results show that the online discourse regarding some topics, such as COVID-19 regulations or conspiracy theories, is highly controversial and reflects the actual U.S. political landscape. © 2023 ACM.

Towards a smart pervasive conversational agent for COVID-19 psychological assistance based on NLP

Diverse countries throughout the world were quar-antined due to the novel pandemic known as COVID-19, even after vaccination,. As a result of this grim circumstance, most socioeconomic and political spheres have encountered deep crisis and from there people have experienced stress, anxiety, depression, and even suicide, In this paper, we propose a smart pervasive conversational agent for psychological assistance during and after COVID-19 quarantine, which could converse with a regular citizen to raise awareness of the genuine threat of the outbreak and the importance of vaccination. Our proposed conversational agent could be able to recognize and manage stress and anxiety using natural language understanding (NLU) and international stress and anxiety scales. The messages given by our agent and its mode of communication may help to alleviate anxiety following the world's lockdown. Our agent's comment threads and management styles may be able to soothe people's worry during the world's lockdown. Our proposed approach is a mobile healthcare service with three interdependent units: an input processing (IP) that performs natural language understanding (NL), a Storage that stores every interaction, and a response manager (RM) that controls the responses of our conversational agent. © 2022 IEEE.

Towards Timeline Generation with Abstract Meaning Representation

Timeline summarization (TLS) is a challenging research task that requires researchers to distill extensive and intricate temporal data into a concise and easily comprehensible representation. This paper proposes a novel approach to timeline summarization using Meaning Representations (AMRs), a graphical representation of the text where the nodes are semantic concepts and the edges denote relationships between concepts. With AMR, sentences with different wordings, but similar semantics, have similar representations. To make use of this feature for timeline summarization, a two-step sentence selection method that leverages features extracted from both AMRs and the text is proposed. First, AMRs are generated for each sentence. Sentences are then filtered out by removing those with no named-entities and keeping the ones with the highest number of named-entities. In the next step, sentences to appear in the timeline are selected based on two scores: Inverse Document Frequency (IDF) of AMR nodes combined with the score obtained by applying a keyword extraction method to the text. Our experimental results on the TLS-Covid19 test collection demonstrate the potential of the proposed approach. © 2023 ACM.

Towards Detection of Cyberbullying in Hinglish Code Mixed Data

Covid-19 eruption and lockdown situation have increased the usages of online platforms which have impacted the users. Cyberbullying is one of the negative outcomes of using social media platforms which leads to mental and physical distress. This study proposes a machine learning-based approach for the detection of cyberbullying in Hinglish text. We use the Hinglish Code-Mixed Corpus, which consists of over 6,000 tweets, for our experiments. We use various machine learning algorithms, including Logistic regression (LR), Multinomial Naive Bayes (MNB), Support vector machine (SVM), Random Forest (RF), to train our models. We evaluate the performance of the models using standard evaluation metrics such as precision, recall, and F1-score. Our experiments show that the LR with Term Frequency-Inverse Document Frequency (TFIDF) outperforms the other models, achieving 92% accuracy. Our study demonstrates that machine learning models can be effective for cyberbullying detection in Hinglish text, and the proposed approach can help identify and prevent cyberbullying on social media platforms. © 2023 Bharati Vidyapeeth, New Delhi.

CovRelex-SE: Adding Semantic Information for Relation Search via Sequence Embedding

In recent years, COVID-19 has impacted all aspects of human life. As a result, numerous publications relating to this disease have been issued. Due to the massive volume of publications, some retrieval systems have been developed to provide researchers with useful information. In these systems, lexical searching methods are widely used, which raises many issues related to acronyms, synonyms, and rare keywrds. In this paper, we present a hybrid relation retrieval system, CovRelex-SE, based on embeddings to provide high-quality search results. Our system can be accessed through the following URL: https://www.jaist.ac.jp/is/labs/nguyen-lab/systems/covrelex-se/. © 2023 Association for Computational Linguistics.

Need for Vision: A data-centric approach towards analysing impact of COVID-19

From the beginning of 2020, we saw a rise of a new virus called the Coronavirus and ultimately a pandemic that anyone reading this paper must have been through. With the rise of COVID,many vaccines were found, the global vaccination drive as a result of this naturally fueled a possibility of Pro-Vaxxers and Anti-Vaxxers strongly expressing their support and concerns regarding the vaccines on social media platforms and along with this came up the need of quick identification of people who are experiencing COVID-19 symptoms. So in this paper, an effort has been made to facilitate the understanding of all these complications and help the concerned authorities. With the help of data in the form of Covid-19 tweets, a (machine-learning) classifier has been built which can classify users as per their vaccine related stance and also classify users who have reported their symptoms through tweets. © FIRE 2022: Forum for Information Retrieval Evaluation.

Moral Narratives Around the Vaccination Debate on Facebook

Vaccine hesitancy is a complex issue with psychological, cultural, and even societal factors entangled in the decision-making process. The narrative around this process is captured in our everyday interactions;social media data offer a direct and spontaneous view of peoples' argumentation. Here, we analysed more than 500,000 public posts and comments from Facebook Pages dedicated to the topic of vaccination to study the role of moral values and, in particular, the understudied role of the Liberty moral foundation from the actual user-generated text. We operationalise morality by employing the Moral Foundations Theory, while our proposed framework is based on recurrent neural network classifiers with a short memory and entity linking information. Our findings show that the principal moral narratives around the vaccination debate focus on the values of Liberty, Care, and Authority. Vaccine advocates urge compliance with the authorities as prosocial behaviour to protect society. On the other hand, vaccine sceptics mainly build their narrative around the value of Liberty, advocating for the right to choose freely whether to adhere or not to the vaccination. We contribute to the automatic understanding of vaccine hesitancy drivers emerging from user-generated text, providing concrete insights into the moral framing around vaccination decision-making. Especially in emergencies such as the Covid-19 pandemic, contrary to traditional surveys, these insights can be provided contemporary to the event, helping policymakers craft communication campaigns that adequately address the concerns of the hesitant population. © 2023 ACM.

Detecting COVID-19 Vaccine Stance and Symptom Reporting from Tweets using Contextual Embeddings

Determining sentiments of the public with regard to COVID-19 vaccines is crucial for nations to efficiently carry out vaccination drives and spread awareness. Hence, it is a field requiring accurate analysis and captures the interest of many researchers. Microblogs from social media websites such as Twitter sometimes contain colloquial expressions or terminology difficult to interpret making the task a challenging one. In this paper, we propose a method for multi-label text classification for the track of”Information Retrieval from Microblogs during Disasters (IRMiDis)” presented by the”Forum of Information Retrieval Evaluation” in 2022, related to vaccine sentiment among the public and reporting of someone experiencing COVID-19 symptoms. The following methodologies have been utilised: (i) Word2Vec and (ii) BERT, which uses contextual embedding rather than the fixed embedding used by conventional natural language models. For Task 1, the overall F1 score and Accuracy are 0.503 and 0.529, respectively, placing us fourth among all the teams, while for Task 2, they are 0.740 and 0.790, placing us second among all the teams who submitted their work. Our code is openly accessible through GitHub. 1 © 2022 Copyright for this paper by its authors.

Context Aware Automatic Subjective and Objective Question Generation using Fast Text to Text Transfer Learning

Online learning has gained a tremendous popularity in the last decade due to the facility to learn anytime, anything, anywhere from the ocean of web resources available. Especially the lockdown all over the world due to the Covid-19 pandemic has brought an enormous attention towards the online learning for value addition and skills development not only for the school/college students, but also to the working professionals. This massive growth in online learning has made the task of assessment very tedious and demands training, experience and resources. Automatic Question generation (AQG) techniques have been introduced to resolve this problem by deriving a question bank from the text documents. However, the performance of conventional AQG techniques is subject to the availability of large labelled training dataset. The requirement of deep linguistic knowledge for the generation of heuristic and hand-crafted rules to transform declarative sentence into interrogative sentence makes the problem further complicated. This paper presents a transfer learning-based text to text transformation model to generate the subjective and objective questions automatically from the text document. The proposed AQG model utilizes the Text-to-Text-Transfer-Transformer (T5) which reframes natural language processing tasks into a unified text-to-text-format and augments it with word sense disambiguation (WSD), ConceptNet and domain adaptation framework to improve the meaningfulness of the questions. Fast T5 library with beam-search decoding algorithm has been used here to reduce the model size and increase the speed of the model through quantization of the whole model by Open Neural Network Exchange (ONNX) framework. The keywords extraction in the proposed framework is performed using the Multipartite graphs to enhance the context awareness. The qualitative and quantitative performance of the proposed AQG model is evaluated through a comprehensive experimental analysis over the publicly available Squad dataset. © 2023, International Journal of Advanced Computer Science and Applications. All Rights Reserved.

How Severe is Your COVID-19? Predicting SARS-CoV-2 Infection with Graph Attention Capsule Networks

Recent studies in machine learning have demonstrated the effectiveness of applying graph neural networks (GNNs) to single-cell RNA sequencing (scRNA-seq) data to predict COVID-19 disease states. In this study, we propose a graph attention capsule network (GACapNet) which extracts and fuses Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2) transcriptomic patterns to improve node classification performance on cells and genes. Significantly different from the existing GNN approaches, we innovatively incorporate a capsule layer with dynamic routing into our model architecture to combine and fuse gene features effectively and to allow those more prominent gene features present in the output. We evaluate our GACapNet model on two scRNA-seq datasets, and the experimental results show that our GACapNet model significantly outperforms state-of-the-art baseline models. Therefore, our study demonstrates the capability of advanced machine learning models to generate predictive features and evolutionary patterns of the SARS-CoV-2 pathogen, and the applicability of closing knowledge gaps in the pathogenesis and recovery of COVID-19. © 2022 IEEE.

Doc-Handler: Document Scanner, Manipulator, and Translator based on Image and Natural language processing

Physical documents may easily be converted into digital versions in the modern digital era by employing scanning software and the internet. The day when this activity needed printers and scanners is long gone. Nowadays, even our smartphones and cameras may be used to quickly convert paper documents into digital ones. This is especially useful in the wake of the COVID-19 pandemic, where the ability to share and access documents online is more important than ever. This study proposes an application for illiterate people to quickly translate scanned papers or photos into their native language and save them in a digital format. The Application makes use of image processing methods and has capabilities including PDF conversion, image colour adjustment, cropping, and Optical Character Recognition (OCR). A user-friendly application, developed using the Flutter Framework and programmed in Python and Dart, serves as the interface for the system. The proposed application is cross-platform and works with a variety of gadgets. This method intends to increase accessibility and productivity for illiterate people in the digital age by integrating image processing with language translation. © 2023 IEEE.

Analyzing the Evolution of Disinformation Content on Facebook - a Pilot Study

Disinformation spread on social media generates a truly massive amount of content on a daily basis, much of it not quite duplicated but repetitive and related. In this paper, we present an approach for clustering social media posts based on topic modeling in order to identify and formalize an underlying structure in all the noise. This would be of great benefit for tracking evolving trends, analyzing large-scale campaigns, and focusing efforts on debunking or community outreach. The steps we took in particular include harvesting through CrowdTangle huge collection of Facebook posts explicitly identified as containing disinformation by debunking experts, following those links back to the people, pages and groups where they were shared then collecting all posts shared on those channels over an extended period of time. This generated a very large textual dataset which was used in the topic modeling experiments attempting to identify the larger trends in the available data. Finally, the results were transformed and collected in a Knowledge Graph for further study and analysis. Our main goal is to investigate different trends and common patterns in disinformation campaigns, and whether there exist some correlations between some of them. For instance, for some of the most recent social media posts related to COVID-19 and political situation in Ukraine. © 2022 Copyright for this paper by its authors.

Exploring Language-Interfaced Fine-Tuning for COVID-19 Patient Survival Classification

We present Language-Interfaced Fine-Tuning (LIFT) in application to COVID-19 patient survival classification. LIFT describes translating tabular Electronic Health Records (EHRs) into text inputs for transformer neural networks. We study LIFT with a dataset of 5,371 COVID-19 patients. We focus on the predictive task of survival classification utilizing demographic and medical history features. We begin by presenting information about our dataset. We preface our investigation in text-based transformers by reporting the performances of conventional machine learning models such as Logistic Regression and Random Forest classifiers. We also present the results of a few configurations of tabular input-based Deep Multilayer Perceptron (MLP) networks. 86% of the patients in our database survived in the measured time window. Thus, predictive models are heavily biased to predict that a patient will survive. We emphasize that this problem of Class Imbalance was a major challenge in developing these models. Our balanced sampling strategy from examples in the majority and minority classes is crucial to achieving even reasonable predictive performance. For this reason, we also report performance based on Precision, Recall, and F-score metrics, in addition to Accuracy. Having established baselines with tabular inputs, we then shift our focus to the prompts for translating from tabular to text inputs. We report the performance of 5 prompts. The LIFT model achieves an F-score on the held-out test set of 0.21, slightly behind the Deep MLP with Tabular Features score of 0.23. Both models outperform the Random Forest with Tabular Features at 0.15. We believe that LIFT is a very exciting direction for machine learning in healthcare applications because text-based inputs enables us to take advantage of recent advances in Transfer Learning and Retrieval-Augmented Learning. This study illustrates the effectiveness of converting tabular EHRs to text inputs and utilizing transformer neural networks for prediction. © 2022 IEEE.

Tweets and PCR Test-based Analysis and Prediction of Social Response to a Future Pandemic. A Case Study

The COVID-19 pandemic has greatly affected our society badly. It has been a subject of discussion since 2019 due to the increased prevalence of social media and its extensive use, and it has been a source of tension, fear, and disappointment for people all over the world. In this research, we took data from COVID-19 tweets from 10 different regions from July 25, 2020, to August 29, 2020. Using the well-known word embedding technique count-vectorizer, we experimented with different machine learning classifiers on data to train deep neural networks to improve the accuracy of predicted opinions with a low elapsed time. In addition, we collected PCR results from these regions for the same time interval. We compared the opinions in the form of positive or negative responses with the results of the PCR tests per million people. With the help of the results, We figured out a real-time international measure to detect these regions' behaviors for any future pandemic. If we know how a region thinks about an upcoming pandemic, then we can predict the region's real-time behavior for the particular pandemic. This would happen if we had past case studies to compare, like in our proposed research. Copyrights © 2023 The Institute of Electronics and Information Engineers.

Exploratory analysis of text using available NLP technologies for Serbian language

This paper combines available NLP technologies for Serbian languages and traditional data science methods in order to analyze collected dataset on the news headlines related to the COVID-19 pandemics. As an addition to NLP technologies for the Serbian language, a specialized database was created in an attempt to enhance the research within the field. Within the paper, the database was exploratory analyzed, and perspectives of the work with the data were thoroughly explored. © 2023 IEEE.

Working With AI to Persuade: Examining a Large Language Model's Ability to Generate Pro-Vaccination Messages

Artificial Intelligence (AI) is a transformative force in communication and messaging strategy, with potential to disrupt traditional approaches. Large language models (LLMs), a form of AI, are capable of generating high-quality, humanlike text. We investigate the persuasive quality of AI-generated messages to understand how AI could impact public health messaging. Specifically, through a series of studies designed to characterize and evaluate generative AI in developing public health messages, we analyze COVID-19 pro-vaccination messages generated by GPT-3, a state-of-the-art instantiation of a large language model. Study 1 is a systematic evaluation of GPT-3's ability to generate pro-vaccination messages. Study 2 then observed peoples' perceptions of curated GPT-3-generated messages compared to human-authored messages released by the CDC (Centers for Disease Control and Prevention), finding that GPT-3 messages were perceived as more effective, stronger arguments, and evoked more positive attitudes than CDC messages. Finally, Study 3 assessed the role of source labels on perceived quality, finding that while participants preferred AI-generated messages, they expressed dispreference for messages that were labeled as AI-generated. The results suggest that, with human supervision, AI can be used to create effective public health messages, but that individuals prefer their public health messages to come from human institutions rather than AI sources. We propose best practices for assessing generative outputs of large language models in future social science research and ways health professionals can use AI systems to augment public health messaging. © 2023 ACM.

Healthcare Industry: Embracing Potential of Big Data across Value Chain

In the fast-moving era of the Industrial Revolution (Industry 4.0), digitally fueled devices and technologies are paramount for driving innovation and creating values across a myriad of industries. A case in point is - Healthcare Industry. Healthcare insurance companies, hospitals, and other providers around the world are belligerently leveraging digital tools and technologies such as Big Data analytics, Lake, Machine Learning, Artificial Intelligence, Internet of Things (IoT), Natural Language Processing, smart sensors, and the Internet of Things (IoT), for improving the overall quality of care and overall process efficiency and effectiveness. The Healthcare industry has been a center of discussion for embracing Big Data practice across the value chain for the past couple of decades due to the prodigious potential that is concealed in it. With so much abundant information, there have been numerous provocations related to the apiece stage of maneuvering big data that can only be amplified by leveraging high-end computer science results for big data analytics, as mentioned above. Well-organized healthcare ecosystem, analysis, and magnification of big data can influence the course of the game by opening new paths in terms of offering unique yet innovative products and services for the modern age technology-propelled healthcare value chain. This paper emphasizes the impetus of Big Data across the healthcare value chain, which involves the amalgamation of technology, data, and business, yielding better decisions and improving the experience across all touch points. © 2022 IEEE.