Overview of the FIRE 2022 track: Information Retrieval from Microblogs during Disasters (IRMiDis)

Microblogging sites such as Twitter play an important role in dealing with various mass emergencies including natural disasters and pandemics. The FIRE 2022 track on Information Retrieval from Microblogs during Disasters (IRMiDis) focused on two important tasks – (i) to detect the vaccine-related stance of tweets related to COVID-19 vaccines, and (ii) to detect reporting of COVID-19 symptom in tweets. © 2022 Copyright for this paper by its authors.

Sentiment Analysis of COVID-19 Tweets Using BiLSTM and CNN-BiLSTM

In a society where people express almost every thought they have on social media, analysing social media for sentiment has become very significant in order to understand what the masses are thinking. Especially microblogging website like twitter, where highly opinionated individuals come together to discuss ongoing socioeconomic and political events happening in their respective countries or happening around the world. For analysing such vast amounts of data generated every day, a model with high efficiency, i.e., less running time and high accuracy, is needed. Sentiment analysis has become extremely useful in this regard. A model trained on a dataset of tweets can help determine the general sentiment of people towards a particular topic. This paper proposes a bidirectional long short-term memory (BiLSTM) and a convolutional bidirectional long short-term memory (CNN-BiLSTM) to classify tweet sentiment;the tweets were divided into three categories—positive, neutral and negative. Specialized word embeddings such as Word2Vec or term frequency—inverse document frequency (tf-idf) were avoided. The aim of this paper is to analyse the performance of deep neural network (DNN) models where traditional classifiers like logistic regression and decision trees fail. The results show that the BiLSTM model can predict with an accuracy of 0.84, and the CNN-BiLSTM model can predict with an accuracy of 0.80. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

An Application of the ELM Model to Information Sharing on Twitter: Studying the Role of Message Form and Sender Profile

This paper focuses on the information sharing behaviour of users within a micro-blogging platform, Twitter. We propose an explanatory model of the performance of a message by taking into account the external cues (source and form of the message) beyond the content and meaning of the text, and we test it empirically, on a corpus of nearly 800,000 original tweets sent by about 235,000 users over a period of 7 months concerning the Covid-19 epidemic in France. We thus show the importance of the source's credibility and its strategy on the platform, but also of the form of the post, its composition and its degree of elaboration. These elements are nuanced by the level of engagement of the source in the topic of conversation on which it intervenes and by the context in which these messages are sent and received. © 2022 Authors. All rights reserved.

Identifying Situational Information during Mass Emergency

In the advent of Natural Language Processing, what finds itself in much use is analysis. This research paper finds itself in reference to the same that enables it in analysing sentiments of a text. The tasks that were covered in working with NLP includes – firstly, differentiating tweets on the basis of claims and facts, and secondly to create an effective classifier that finds out if a tweet is anti-covid vaccine, pro-covid vaccine or neutral. The beauty of our paper resides in the fact, that we have hit high end accuracies without using hefty algorithms, namely 93% for the first task using Random Forest and 45.4% for the second task using BERT’s Algorithm. Our accuracies are the best among all the teams working on the same tasks, which deepens the effect that this paper resonates. The details of the IRMiDis 2021 data challenge have been discussed elaborately here, and we hope our paper marks its significance by virtue of its own merit. © 2021 Copyright for this paper by its authors.

Analyzing COVID-19 Vaccination

The outbreak of the coronavirus has resulted in unprecedented action, which has led authorities to decide to begin the blockade of the areas most hit by the infectious disease. Social media has been an important support for people during this difficult time. On November 9, 2020, when the first vaccine with an infection rate of 90% or higher was announced, social media responded with, and people around the world began to express the feelings of vaccination. It was no longer a hypothesis, but closer to,every day to become a reality Therefore, it becomes imperative to verify some of the information posted on social media during the pandemic situation, specially related to Covid vaccines. To this end, it is necessary to correctly identify fact-checkable posts, so that their information content can be verified.In this work, we have addressed the problem to identify 3 types of classification on the Twitter microblogging site. We organized a shared task in the FIRE 2021 conference to study the problem of identifyefficient classifier for prediction tweets posted during a particular pandemic scenario (the Covid 19). This paper describes the dataset used in the shared task, and compares the performance of different classification that are provax, antivax and last neutraal for identifying effective tweets related to Covid vaccines.We experimented with a classification-based approach. Our experiment shows that SVM classification performs well in order to effiective posts.Using this support vector machine in order to solve the antivax, provax,neutral classification of twets .We’re going to do this because vaccination is an important step for Covid19 so people can easily fix the news about the vaccine and grab their own slot. © 2021 Forum for Information Retrieval Evaluation, December 13-17, 2021, India.

Exploiting Diverse Contextual Features through Transformers for Detecting Informative Tweets

Twitter is deemed the most reliable and convenient microblogging platform for getting real-time news and information. During the COVID-19 pandemic, people are keen to share various information ranging from new cases, healthcare guidelines, medication, and vaccine news on Twitter. However, a major portion of the shared tweets is uninformative and misleading which may create mass panic. Hence, it is an important task to distinguish and label a COVID-19 tweet as informative or uninformative. Prior works mostly focused on various pretrained transformer models and different types of contextual feature extractors to address this task. However, most of the works applied these models one at a time and didn't employ any effective neural layer at the bottom to distill the tweet contexts effectively. Since a tweet may contain a multifarious context, therefore, representing a tweet using only one kind of feature extractor may not work well. To overcome this limitation, we present an approach that leverages an ensemble of various cutting-edge transformer models to capture the diverse contextual dimension of the tweets. We exploit the BERT, CTBERT, BERTweet, RoBERTa, and XLM-RoBERTa models in our proposed method. Next, we perform a pooling operation on those extracted embedding features to transform them into document embedding vectors. Then, we utilize a feed-forward neural architecture with a linear activation function for the classification task. To generate final prediction, we utilize the majority voting-driven ensemble technique. Experiments on WNUT-2020 COVID-19 English Tweet dataset manifested the efficacy of our method over other state-of-the-art methods. © 2022 IEEE.

Measuring Online Trust in Government Microblogs in Public Health Emergencies

[Objective] This paper tries to measure the netizens' trust in government microblogs during public health emergencies, and then explores reasons for the changes. [Methods] First, we calculated the trust from the comments on government microblogs with the comment objects, the topic similarity between comments and microblogs, as well as their sentiments. Then, we added the numbers of likes and forwards/retweets to decide the comprehensive trust of the netizens toward the government microblogs. [Results] We examined out model with microblog data on COVID-19 and found that topics related to industrial and government efforts fighting the pandemic enhanced the trust in government microblogs. There were great differences in the development trends and reasons of the trust in government microblogs from different fields. [Limitations] We only used the events and the microbloggers as the objects of comments. [Conclusions] The proposed model could help government agencies improve decision making, public trust, and lead online opinion during public health emergencies. © 2022, Chinese Academy of Sciences. All rights reserved.

How to Save Lives with Microblogs? Lessons From the Usage of Weibo for Requests for Medical Assistance During COVID-19

During recent crises like COVID-19, microblogging platforms have become popular channels for affected people seeking assistance such as medical supplies and rescue operations from emergency responders and the public. Despite this common practice, the affordances of microblogging services for help-seeking during crises that needs immediate attention are not well understood. To fill this gap, we analyzed 8K posts from COVID-19 patients or caregivers requesting urgent medical assistance on Weibo, the largest microblogging site in China. Our mixed-methods analyses suggest that existing microblogging functions need to be improved in multiple aspects to sufficiently facilitate help-seeking in emergencies, including capabilities of search and tracking requests, ease of use, and privacy protection. We also find that people tend to stick to certain well-established functions for publishing requests, even after better alternatives emerge. These findings have implications for designing microblogging tools to better support help requesting and responding during crises. © 2022 ACM.

Twitter Sentiment Analysis: Caribbean Prime Ministers Response to COVID-19 Pandemic

In today's world, millions of people use social networking and microblogging sites every day to share their views, opinions, and emotions in their daily lives. These sites can become an invaluable source for data mining and can be used effectively to evaluate people's opinion on a product, an entity or perhaps topics of interest. Sentiment Analysis, as it is called, allows us to determine whether the opinions, mood, views, or attitude in a text is either 'positive', 'negative', or 'neutral'. The focus of this study was to analyze the tweets of the top ten English-speaking Caribbean Prime Ministers on Twitter to determine how effective they were in reducing the spread of the COVID-19 outbreak in their territories. The research results provided clear evidence that the negative sentiment towards the virus by the Caribbean leaders was a contributing factor in reducing the number of cases and deaths during the first five months of COVID-19 in the region. The results also found that a correlation exists between the prime ministers' social network and their effectiveness in managing the virus. In addition, the words expressed by the prime ministers in reference to COVID-19 were clear and practical therefore making it easier for the prime ministers to implement strict measures to control the spread of the virus in the region. © 2021 IEEE.

Sentiment Analysis of Microblogging Dataset on Coronavirus Pandemic

Sentiment analysis can largely influence the people to get the update of the current situation. Coronavirus (COVID-19) is a contagious illness caused by the SARS-CoV-2 virus that causes severe respiratory symptoms. The lives of millions have continued to be affected by this pandemic, several countries have resorted to a full lockdown. During this lockdown, people have taken social networks to express their emotions to find a way to calm themselves down. People are spreading their sentiments through microblogging websites as one of the most preventive steps of this disease is the socialization to gain people's awareness to stay home and keep their distance when they are outside home. Twitter is a popular online social media platform for exchanging ideas. People can post their different sentiments, which can be used to aware people. But, some people want to spread fake news to frighten the people. So, it is necessary to identify the positive, negative, and neutral thoughts so that the positive opinions can be delivered to the mass people for spreading awareness to the people. Moreover, a huge volume of data is floating on Twitter. So, it is also important to identify the context of the dataset. In this paper, we have analyzed the twitter dataset for evaluating the sentiment using several machine learning algorithms, where the random forest algorithm achieved the highest accuracy of 93%. Later, we have found out the context learning of the dataset based on the sentiments. © 2021 IEEE.

Exploiting Ensemble of Transformer Models for Detecting Informative Tweets

Microblogging platforms especially Twitter is considered as one of the prominent medium of getting user-generated information. Millions of tweets were posted daily during COVID-19 pandemic days and the rate increases gradually. Tweets include a wide range of information including healthcare information, recent cases, and vaccination updates. This information helps individuals stay informed about the situation and assists safety personnel in making decisions. Apart from these, large amounts of propaganda and misinformation have spread on Twitter during this period. The impact of this infodemic is multifarious. Therefore, it is considered a formidable task to determine whether a tweet related to COVID-19 is informative or uninformative. However, the noisy and nonformal nature of tweets makes it difficult to determine the tweets' informativeness. In this paper, we propose an approach that exploits the benefits of finetuned transformer models for informative tweet identification. Upon extracting features from pre-trained COVID-Twitter-BERT and RoBERTa models, we leverage the stacked embedding technique to combine them. The features are then fed to a BiLSTM module to learn the contextual dimension effectively. Finally, a simple feed-forward linear architecture is employed to obtain the predicted label. Experimental result on WNUT-2020 benchmark informative tweet detection dataset demonstrates the potency of our method over various state-of-the-art approaches. © 2021 IEEE.

A Review of Spam Detection in Social Media

With significant usage of social media to socialize in virtual environments, bad actors are now able to use these platforms to spread their maUcious activities such as hate speech, spam, and even phishing to very large crowds. Especially, Twitter is suitable for these types of activities because it is one of the most common social media platforms for microblogging with millions of active users. Moreover, since the end of 2019, Covid-19 has changed the lives of individuals in many ways. While it increased social media usage due to free time, the number of cyber-attacks soared too. To prevent these activities, detection is a very crucial phase. Thus, the main goal of this study is to review the state-of-art in the detection of malicious content and the contribution of AI algorithms for detecting spam and scams effectively in social media. © 2021 IEEE

Two-stage Clustering Method for Discovering People's Perceptions: A Case Study of the COVID-19 Vaccine from Twitter

Twitter is currently one of the most influential microblogging services on which users interact with messages. It is imperative to grasp the big picture of Twitter through analyzing its huge stream data. In this study, we develop a two-stage clustering method that automatically discovers coarse-grained topics from Twitter data. In the first stage, we use graph clustering to extract micro-clusters from the word co-occurrence graph. All the tweets in a micro-cluster share a fine-grained topic. We then obtain the time series of each micro-cluster by counting the number of tweets posted in a time window. In the second stage, we use time series clustering to identify the clusters corresponding to coarse-grained topics. We evaluate the computational efficacy of the proposed method and demonstrate its systematic improvement in scalability as the data volume increases. Next, we apply the proposed method to large-scale Twitter data (26 million tweets) about the COVID-19 Vaccination in Japan. The proposed method separately identifies the reactions to news and the reactions to tweets. © 2021 IEEE.

Overview of the FIRE 2021 track: Information Retrieval from Microblogs during Disasters (IRMiDis)

Microblogging sites such as Twitter play an important role in dealing with various mass emergencies including natural disasters and pandemics. The FIRE2021 track on Information Retrieval from Microblogs during Disasters (IRMiDis) focused on two important tasks - (i) to identify claims or fact-checkable tweets, which is the first step towards verifying information posted on social media, and (ii) to detect the vaccine-related stance of tweets related to COVID-19 vaccines. © 2021 Owner/Author.

Tracking public opinion about online education over COVID-19 in China.

Due to the novel coronavirus disease (COVID-19) outbreak in China, a large number of Chinese students resorted to online learning resources. The increasingly widespread online education enables the investigation of public opinion about this large-scale untraditional mode of learning during this critical period. Sina Weibo Microblogs (the Chinese equivalent of Twitter) related to online education were collected in three distinctive phases: from July 01, 2019 to January 09, 2020 (pre-pandemic); from January 10, 2020 to April 30, 2020 (amid-pandemic); and from May 01, 2020 to Nov 30, 2020 (post-pandemic), respectively. The aim was to obtain broad insight into how online learning was viewed by the public in the Chinese educational landscape. The public opinion during these three periods were analysed and compared. The findings facilitated a better understanding of what the Chinese public perceived about this online learning mode in becoming the dominant channel for teaching and learning during critical periods.

Twitter for microblogging in oral health care, research, and academics: Road map and future directions.

Current times have seen growing use of social medial tools, including microblogging sites like Twitter as an efficient method to disseminate information related to health amongst patients, students as well as health care workers. This article explores the role of this short, effective messaging platform in oral health care, teaching, research and learning. The concepts of "tweeting the meeting" and aggregation of conversations via "hashtags" is advocated for academic conferences, which will extend the conference reach to give the users better access to the instructors and enhance the related outcomes. Tweeting and retweeting the required research content may increase the academic footprint of the conducted research and researchers. In addition, it has served an immense role in the current COVID-19 pandemic by the regular circulation of information to the public and helped governments in policymaking and showcasing the areas of public concern. However, it still has a huge potential yet to be explored, with collective efforts towards strengthening the aspects of authenticity and standardization of the shared content.

Tweets by People With Arthritis During the COVID-19 Pandemic: Content and Sentiment Analysis.

BACKGROUND: Emerging evidence suggests that people with arthritis are reporting increased physical pain and psychological distress during the COVID-19 pandemic. At the same time, Twitter's daily usage has surged by 23% throughout the pandemic period, presenting a unique opportunity to assess the content and sentiment of tweets. Individuals with arthritis use Twitter to communicate with peers, and to receive up-to-date information from health professionals and services about novel therapies and management techniques. OBJECTIVE: The aim of this research was to identify proxy topics of importance for individuals with arthritis during the COVID-19 pandemic, and to explore the emotional context of tweets by people with arthritis during the early phase of the pandemic. METHODS: From March 20 to April 20, 2020, publicly available tweets posted in English and with hashtag combinations related to arthritis and COVID-19 were extracted retrospectively from Twitter. Content analysis was used to identify common themes within tweets, and sentiment analysis was used to examine positive and negative emotions in themes to understand the COVID-19 experiences of people with arthritis. RESULTS: In total, 149 tweets were analyzed. The majority of tweeters were female and were from the United States. Tweeters reported a range of arthritis conditions, including rheumatoid arthritis, systemic lupus erythematosus, and psoriatic arthritis. Seven themes were identified: health care experiences, personal stories, links to relevant blogs, discussion of arthritis-related symptoms, advice sharing, messages of positivity, and stay-at-home messaging. Sentiment analysis demonstrated marked anxiety around medication shortages, increased physical symptom burden, and strong desire for trustworthy information and emotional connection. CONCLUSIONS: Tweets by people with arthritis highlight the multitude of concurrent concerns during the COVID-19 pandemic. Understanding these concerns, which include heightened physical and psychological symptoms in the context of treatment misinformation, may assist clinicians to provide person-centered care during this time of great health uncertainty.