Search

Background: One of the psychological problems that have become very prevalent in the modern world is depression, where mental health disorders have become very common. Depression, as reported by the WHO, is the second-largest factor in the worldwide burden of illnesses. As these issues grow, social media has become a tremendous platform for people to express themselves. A user's social media behavior may therefore disclose a lot about their emotional state and mental health. This research offers a novel framework for depression detection from Arabic textual data utilizing deep learning (DL), natural language processing (NLP), machine learning (ML), and BERT transformers techniques in light of the disease's high prevalence. To do this, a dataset of tweets was used, which was collected from 3 sources, as we mention later. The dataset was constructed in two variants, one with binary classification and the other with multi-classification. Results: In binary classifications, we used ML techniques such as "support vector machine (SVM), random forest (RF), logistic regression (LR), and Gaussian naive Bayes (GNB)," and used BERT transformers "ARABERT." In comparison ML with BERT transformers, ARABERT has high accuracy in binary classification with a 93.03 percent accuracy rate. In multi-classification, we used DL techniques such as "long short-term memory (LSTM)," and used BERT transformers "Multilingual BERT." In comparison DL with BERT transformers, multilingual has high accuracy in multi-classification with an accuracy of 97.8%. Conclusion: Through user-generated content, we can detect depressed people using artificial intelligence technology in a fast manner and with high accuracy instead of medical technology. [ABSTRACT FROM AUTHOR]

Event-based surveillance is crucial for the early detection and rapid response to potential public health risks. In recent years, social networking services (SNS) have been recognized for their potential role in this domain. Previous studies have demonstrated the capacity of SNS posts for the early detection of health crises and affected individuals, including those related to infectious diseases. However, the reliability of such posts, being subjective and not clinically diagnosed, remains a challenge. In this study, we address this issue by assessing the classification performance of transformer-based pretrained language models to accurately classify Japanese tweets related to heat stroke, a significant health effect of climate change, as true or false. We also evaluated the efficacy of combining SNS and artificial intelligence for event-based public health surveillance by visualizing the data on correctly classified tweets and heat stroke emergency medical evacuees in time–space and animated video, respectively. The transformer-based pretrained language models exhibited good performance in classifying the tweets. Spatiotemporal and animated video visualizations revealed a reasonable correlation. This study demonstrates the potential of using Japanese tweets and deep learning algorithms based on transformer networks for event-based surveillance at high spatiotemporal levels to enable early detection of heat stroke risks. [ABSTRACT FROM AUTHOR]

Predicting the currency exchange rate is crucial for financial agents, risk managers, and policymakers. Traditional approaches use publicly announced news on macroeconomic and financial variables as predictors of currency exchange. However, the rise of social media may have changed the source of information. For instance, tweets can help investors make informed decisions about the foreign exchange (FX) market by reflecting market sentiment and opinion. From another aspect, changes in currency exchange may incite agents to post tweets. Are tweets good predictors of currency exchange? Is the relationship between tweets and currency exchange bidirectional? We investigate the comovement/causality between the number of #dolar ("enflasyon" resp.) tweets and USDTRY currency exchange using wavelet coherence and transfer entropy (TE) to answer these questions. Wavelet coherence allows us to determine the relationship between the number of tweets and the USDTRY rate by considering the time–frequency domain. TE enables us to quantify the net information flow between the number of tweets and USDTRY. Data from October 2020 to March 2022 were used. The obtained results remain robust regardless of the frequency of retained data (daily or hourly) and the methods used (wavelet or TE). Based on our results, USDTRY is correlated with the number of #dolar tweets (#inflation) mainly in the short run and a few times in the medium run. These relationships change through time and frequency (wavelet analysis results). However, the results from TE indicate a bidirectional relationship between the #dolar (#inflation) tweets number and the USDTRY exchange rate. The influence of the exchange rate on the number of tweets is highly pronounced. Financial agents, risk managers, policymakers, and investors should then pay moderate attention to the number of #dolar (#inflation) tweets in trading/forecasting the USD–TRY exchange rate. [ABSTRACT FROM AUTHOR]

Introduction: Engagement with mobile health (mHealth) technologies among patients with hypertension is linked to reduced blood pressure and improved patient understanding of the condition. Aim: This study aimed to evaluate the psychometric properties (validity and reliability) of the TWente Engagement with Ehealth Technologies Scale (TWEETS) in an Italian cohort with hypertension. This study is the first attempt to evaluate the psychometric characteristics of the TWEETS in this population. Methods: The study was conducted in three phases. The first phase encompassed the translation and cultural adaptation of the TWEETS to the Italian setting. The second phase involved an expert panel evaluating the instrument's face and content validities. The third phase was a cross-sectional study aiming to test construct validity and reliability. Adults diagnosed with hypertension were eligible for participation. Additional inclusion criteria included stable antihypertensive treatment for at least 2 weeks before enrolment and the provision of written informed consent. Patients were taught how to use two mHealth devices using the teach-back method. Results: A total of 131 patients were enrolled. Exploratory and confirmatory factor analyses revealed that the TWEETS had a one-factor structure and a good level of fit. Cronbach's alpha coefficients suggested good internal consistency. Conclusions: The findings indicate that the TWEETS is a valuable tool for assessing the engagement of patients with hypertension with mHealth devices. Further assessment is needed in various cohorts to confirm the psychometric equivalence of the construct across different groups with hypertension. [ABSTRACT FROM AUTHOR]

The majority of educational institutions around the world have switched to online learning due to the COVID-19 pandemic. Since continuing education has become important during the pandemic as well, academics and students have recognized the value of online learning to avoid their challenges. The objective of this study is to categorize peoples' opinions and determine how the community used online learning during the pandemic. A total of 13,155 tweets were collected using the Twitter API. Of these, 4486 were positive about the online learning process, 4490 were negative, and 4179 were advertising for online learning. After pre-processing the tweets, Term Frequency-Inverse Document Frequency (TF-IDF) vectorizer is used to extract the feature vectors. The data was divided into three categories using the Long Short Term Memory (LSTM) and Support Vector Machine (SVM) algorithms. Sentiment analysis is used to determine how society feels about the online learning process by analyzing positive, negative, and advertisement sentiments. According to the results, LSTM beat SVM and achieved an accuracy of 88.58%. It also achieved higher precision, recall, f-measure values, and lowest error rates for 65% of the training dataset. Based on the findings, the significance of online learning as well as the absence of technologies, the internet, and other subpar educational practices were determined. It was determined that more workable solutions were needed in order to improve online education globally. [ABSTRACT FROM AUTHOR]

A large number of users around the globe have preferred to read news and the latest information from the Internet, especially social media, leaving behind the traditional approach of print media. On the one hand, the Internet is a constructive medium to spread the latest news and information briefly. On the other hand, malicious users are very active on the Internet and spread fake news, which becomes viral within a few minutes. The spread of fake news has become a serious threat as many users now rely on Internet news without verification. In this digital world, it is easy to spread any toxic information over the Internet, like hate speech, extremism, propaganda, and political agendas. It is a big challenge in today's digital world to mitigate the spread of fake news; hence, there is a need for an automatic computational tool that can assist in measuring the credibility of news. This study aims to deliver a solution where fake news from Twitter and website-based articles can be detected using the Natural Language Processing (NLP) technique, Bidirectional Encoder Representations from Transformers (BERT), other machine learning classification algorithms, and manual program-based approaches. A dataset with fake and real labels for the textual content is used. Different classification algorithms are evaluated to find a suitable algorithm for delivering a fake news detector. The evaluations are based on machine learning and a program-based approach. The textual content that the user provides, such as an article or tweet, can confirm the legitimacy of fake news. This website offers fake news detection for both website-based news articles and tweets from Twitter in English, Arabic, and Urdu. [ABSTRACT FROM AUTHOR]

Recent studies on the COVID-19 pandemic indicated an increase in the level of anxiety, stress, and depression among people of all ages. The World Health Organization (WHO) recently warned that even with the approval of vaccines by the Food and Drug Administration (FDA), population immunity is highly unlikely to be achieved this year. This paper aims to analyze people's sentiments during the pandemic by combining sentiment analysis and natural language processing algorithms to classify texts and extract the polarity, emotion, or consensus on COVID-19 vaccines based on tweets. The method used is based on the collection of tweets under the hashtag #COVIDVaccine while the nltk toolkit parses the texts, and the tf-idf algorithm generates the keywords. Both n-gram keywords and hashtags mentioned in the tweets are collected and counted. The results indicate that the sentiments are divided into positive and negative emotions, with the negative ones dominating. [ABSTRACT FROM AUTHOR]

Even though the widespread distribution of social network platforms offered credible benefits for people to share information, its rapid development has attracted various attackers. In recent times, the threatening activities of spammers increased rigorously resulting in information security vulnerabilities. An efficient spam detector module is required to accurately categorize spam tweets from legitimate tweets. To fulfill this requirement, an effective spam detection mechanism using a multilayer bidirectional stacked recurrent unit-based quantum chaotic butterfly (MBiSR-QCB) approach is designed in this paper. In order to avoid misclassification issues of the proposed MBiSR-QCB approach, expert knowledge is taken into consideration to make optimal decisions. Aiming at reducing the expert's workload, the tweets are initially processed through the proposed MBiSR-QCB approach, which filters out the non-spam tweets from the spam tweets in a very short duration. The spam tweets distinguished by the proposed MBiSR-QCB approach are further investigated by the expert to prevent the probability of selecting non-spam tweets as spam tweets. The expert performs in-depth analysis and finally categorizes them into true spam tweets and true non-spam tweets. Despite the collaborated operation, the spam detection accuracy achieved is mainly because of the proposed MBiSR-QCB approach. The parallel pattern learning operations of stacked bidirectional gated recurrent unit (SBi-GRU) and multilayer bidirectional long short-term memory (MBiLSTM) with an optimal setting of hyperparameters by quantum chaotic butterfly optimization (QCBO) algorithm increases the spam detection accuracy. The proposed MBiSR-QCB approach's effectiveness is examined using various metrics such as precision, accuracy, sensitivity, F1-measure, and specificity. The simulation result manifests the enhanced performance of the proposed MBiSR-QCB approach over other compared existing techniques, particularly with higher spam detection accuracy of about 98.7%. [ABSTRACT FROM AUTHOR]

Nowadays, an enormous amount of data is available on the WWW and exponentially growing as well. A lot of users use social networking websites such as Twitter, Facebook, Instagram, and Google+ as common platforms for sharing and exchanging views and opinions on any topics/events. The researchers have considered the reviews and views of the users on these platforms for sentiment analysis, opinion mining, question answering, text summarization, etc. The paper proposes a novel approach for identifying reviews or opinion of users having sarcasm in the text patterns at the clause level. The sentences are classified into four categories such as Simple Sentences, Compound Sentences, Complex Sentences, and Compound-Complex Sentences based on the rules derived from a decision tree. The Simple Sentences and Complex Sentences alone are considered for analysing the sentence patterns where a positive sentiment contrasts with a negative polarity and vice-versa. The decision tree and neuro-fuzzy rules are used on sentence structures to classify the sentences into sarcastic and non-sarcastic sentence patterns. Membership functions are used to map the fuzzy rules and linguistic grading is used for grading the sarcastic patterns. The proposed approach is evaluated on Twitter Dataset and found that the results are promising with the recent and relevant work. [ABSTRACT FROM AUTHOR]

With the increased use of social network sites, such as Twitter, attackers exploit these platforms to spread counterfeit content. Such content can be fake advertisements or illegal content. Classifying such content is a challenging task, especially in Arabic. The Arabic language has a complex structure and makes classification tasks more difficult. This paper presents an approach to classifying Arabic tweets using classical machine learning (non-deep machine learning) and deep learning techniques. Tweets corpus were collected through Twitter API and labelled manually to get a reliable dataset. For an efficient classifier, feature extraction is applied to the corpus dataset. Then, two learning techniques are used for each feature extraction technique on the created dataset using N-gram models (uni-gram, bi-gram, and char-gram). The applied classical machine learning algorithms are support vector machines, neural networks, logistics regression, and naïve Bayes. Global vector (GloVe) and fastText learning models are utilised for the deep learning approaches. The Precision, Recall, and F1-score are the suggested performance measures calculated in this paper. Afterwards, the dataset is increased using the synthetic minority oversampling technique class to create a balanced dataset. After applying the classical machine learning models, the experimental results show that the neural network algorithm outperforms the other algorithms. Moreover, the GloVe outperforms the fastText model for the deep learning approach. [ABSTRACT FROM AUTHOR]

The COVID-19 pandemic has led to the emergence of social media platforms as crucial channels for the dissemination of information and public opinion. Comprehending the sentiment conveyed in tweets on COVID-19 is of paramount importance for individuals involved in policymaking, crisis management, and public health administration. This study seeks to conduct a comprehensive review of the current BERT and deep CNN models utilized in sentiment analysis of COVID-19 tweets. Additionally, the study aims to propose potential future research directions for the development of a BERT model that is both lightweight and high quality. The BERT model acquires contextual representations of words and effectively captures the intricate semantics of tweets related to COVID-19, whereas the deep CNN captures the hierarchical organization of the tweet embeddings. The performance of the model is exceptional, exceeding the current sentiment analysis methods for tweets related to COVID-19. Our study involves a comprehensive analysis of vast COVID-19 tweet datasets, wherein we establish the efficacy of the BERT-deep CNN models in precisely categorizing the sentiment of COVID-19 tweets in real time. The outcomes of the research offer significant perspectives on the public's attitudes, supporting decision-makers in comprehending the general viewpoint, detecting disinformation, and guiding emergency response tactics. Additionally, this study serves to enhance the progress of sentiment analysis methodologies within the realm of public health emergencies and establishes a standard for forthcoming investigations in the sentiment analysis of social media data pertaining to COVID-19. [ABSTRACT FROM AUTHOR]

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. [ABSTRACT FROM AUTHOR]

There is significant global concern about the harmful effects of greenhouse gas and carbon monoxide emissions (deforestation, air pollution, global warming, etc.). The 2015 Paris Agreement on climate change aspires to reduce global warming by achieving a climate-neutral world. Research has been carried out to calculate and diminish the aforementioned emissions in waste, power industry, transport, building, in addition to other areas. The aim of this paper is to analyse the carbon and greenhouse gas emissions across countries around the globe in order to find patterns and correlate them to socio-economic indicators [gross national income (GNI), industrial production (IPI) and human development indexes (HDI)] as well as Twitter interactions regarding climate change. For this purpose, time series and socio-economic data have been downloaded from different repositories including EDGAR (Emissions Database for Global Atmospheric Research), World Bank and UNDP (United Nations Development Programme). Although classical clustering algorithms have already been used in the examination of some environmental issues, we use a non-parametric time series clustering method, which has been suggested in certain scientific literature as a more flexible approach, since any ad hoc parametric assumptions are required. The chosen socio-economic indicators have also demonstrated their relevance in pieces of research related to various fields. With respect to Twitter, which is one of the most popular social networks nowadays, significant analysis has also been performed on the basis of capturing citizens’ perceptions on a multitude of matters. We found that several countries such as Brazil, India, China, Nigeria, Russia, United States, Spain, Andorra, Greece, and Qatar show differences in carbon and greenhouse gas emissions patterns. Besides, there does not seem to be a correlation between GNI, IPI and HDI as well as the above mentioned emissions (correlation < 0.16). Regarding Twitter interactions, a dissimilarity in the distribution of hashtags was detected between the aforementioned countries and the rest of the world. This research can help to identify countries in which more governmental measures are needed to reduce the type of emissions analysed in certain industrial sectors. In addition, it points out the topics related to climate change that seem to generate the most debate on Twitter for countries with an unusual pattern. [ABSTRACT FROM AUTHOR]

People start posting tweets containing texts, images, and videos as soon as a disaster hits an area. The analysis of these disaster-related tweet texts, images, and videos can help humanitarian response organizations in better decision-making and prioritizing their tasks. Finding the informative contents which can help in decision making out of the massive volume of Twitter content is a difficult task and require a system to filter out the informative contents. In this paper, we present a multi-modal approach to identify disaster-related informative content from the Twitter streams using text and images together. Our approach is based on long-short-term-memory and VGG-16 networks that show significant improvement in the performance, as evident from the validation result on seven different disaster-related datasets. The range of F1-score varied from 0.74 to 0.93 when tweet texts and images used together, whereas, in the case of only tweet text, it varies from 0.61 to 0.92. From this result, it is evident that the proposed multi-modal system is performing significantly well in identifying disaster-related informative social media contents. [ABSTRACT FROM AUTHOR]

The present study aimed to explore how tweeters' opinions about open access publishing and its main features evolved over time. Using a quantitative content analysis method through an opinion mining approach, it explored a sample of English tweets on open access posted from 2007 to December 2019. The main terms related to open access were first identified through reviewing the related literature and were then categorized into five features including "costs & funding", "impact", "models", "publishing & publications", and "quality & quality control". The terms were composed in the form of search formulae. The searches on Twitter led to retrieving 629,123 tweets. A cleansing process was carried out to remove duplicates, non-English, and low-relevant tweets. The final sample reached 80,629 tweets. The tweets were then tagged with the five features. The KNIME data mining tool and SentiStrength were used respectively for processing the tweets' contents and calculating their opinion scores. According to the results, the open-access-related tweets have been growing based on a sigmoidal model. They were mostly neutral and opinion tweets were far lower in number. The tweets in different polarities have been increasing based on a power-law model, with the negative tweets experiencing a disproportionately higher increase. The positive and negative opinions have remained almost stable in strength, with the former being stronger. The results were almost in line with the previous surveys confirming the co-existence of the positive and negative attitudes about open access. However, the social sphere has been gradually becoming more negative. As attitudes are likely to go viral on social networks, and thereby affect users' perceptions and behaviors, the results call for devising appropriate measures to empower the movement and to find solutions for the problems and concerns leading to the negative opinions. [ABSTRACT FROM AUTHOR]

Online social platforms or social platforms such as Twitter, Facebook and Instagram have become popular platforms for a public discussion about social topics. Recent studies show that there is a growing tendency for people to talk about COVID-19 pandemic in these online channels. The rapid growth of the infected cases by COVID-19 pandemic makes a lots of anxiety and fear among people. With the recent released of Pfizer vaccine, people start posting a lot of rumors regarding the safety concerns of the vaccine, especially among the elderly people. The aim of this study is to bring out the fact that tweets containing all pertinent details about the COVID-19 vaccine and provides an analysis and understanding of users emotions regarding the recent release of COVID-19 vaccine. This study starts with the collection of tweets related to COVID-19 vaccine and then cleaning the dataset from redundant tweets. In this study, we use Twitter API and Web Scraping techniques to obtain a sample of 50,000 tweets talking about COVID-19 vaccine.Further, The analysis of users emotions is achieved by manually labeling and classifying the tweets to either positive or negative. Then, a deep learning based model is used to train the data and classify the people opinion about COVID-19 vaccine. The experimental results illustrate that high percentage of people have shown a positive attitude towards COVID1-19 vaccine. The proposed method is validated over Twitter datasets and the results also demonstrate that use of deep learning classifier can successfully improve the accuracy of people emotions analysis with an accuracy up to 98% for training set and the accuracy for testing set is 73%. [ABSTRACT FROM AUTHOR]

We have proposed MultiLexANFIS which is an adaptive neuro-fuzzy inference system (ANFIS) that incorporates inputs from multiple lexicons to perform sentiment analysis of social media posts. We classify tweets into two classes: neutral and non-neutral; the latter class includes both positive and negative polarity. This type of classification will be considered for applications that aim to test the neutrality of content posted by the users in social media platforms. In our proposed model, features are extracted by integrating natural language processing with fuzzy logic; hence, it is able to deal with the fuzziness of natural language in a very efficient and automatic manner. We have proposed a novel set of 64 rules for the proposed neuro-fuzzy network that can classify tweets correctly by working on fuzzy features fetched from VADER, AFINN and SentiWordNet lexicons. The proposed novel rules are domain independent, i.e., we can extend these rules for any textual data that employs lexicons. The antecedent and consequent parameters of the ANFIS are optimized by gradient descent and least squares estimate algorithms, respectively, in an iterative manner. The key contributions of this paper are: (1) a novel neuro-fuzzy system: MultiLexANFIS that takes as its input the positive and negative sentiment scores of tweets computed from multiple lexicons—VADER, AFINN and SentiWordNet, in order to classify the tweets into neutral and non-neutral content, (2) a novel set of 64 rules for the Sugeno-type fuzzy inference system—MultiLexANFIS, (3) single-lexicon-based ANFIS variants to classify tweets when multiple lexicons are not available and (4) comparison of MultiLexANFIS with different fuzzy, non-fuzzy and deep learning state of the art on various benchmark datasets revealing the superiority of our proposed neuro-fuzzy system for social sentiment analysis. [ABSTRACT FROM AUTHOR]

Twitter has nowadays become a trending microblogging and social media platform for news and discussions. Since the dramatic increase in its platform has additionally set off a dramatic increase in spam utilization in this platform. For Supervised machine learning, one always finds a need to have a labeled dataset of Twitter. It is desirable to design a semi-supervised labeling technique for labeling newly prepared recent datasets. To prepare the labeled dataset lot of human affords are required. This issue has motivated us to propose an efficient approach for preparing labeled datasets so that time can be saved and human errors can be avoided. Our proposed approach relies on readily available features in real-time for better performance and wider applicability. This work aims at collecting the most recent tweets of a user using Twitter streaming and prepare a recent dataset of Twitter. Finally, a semi-supervised machine learning algorithm based on the self-training technique was designed for labeling the tweets. Semi-supervised support vector machine and semi-supervised decision tree classifiers were used as base classifiers in the self-training technique. Further, the authors have applied K means clustering algorithm to the tweets based on the tweet content. The principled novel approach is an ensemble of semi-supervised and unsupervised learning wherein it was found that semi-supervised algorithms are more accurate in prediction than unsupervised ones. To effectively assign the labels to the tweets, authors have implemented the concept of voting in this novel approach and the label pre-directed by the majority voting classifier is the actual label assigned to the tweet dataset. Maximum accuracy of 99.0% has been reported in this paper using a majority voting classifier for spam labeling. [ABSTRACT FROM AUTHOR]

The paper features an analysis of former President Trump's early tweets on COVID-19 in the context of Dr. Fauci's recently revealed email trove. The tweets are analysed using various data mining techniques, including sentiment analysis. These techniques facilitate exploration of content and sentiments within the texts, and their potential implications for the national and international reaction to COVID-19. The data set or corpus includes 159 tweets on COVID-19 that are sourced from the Trump Twitter Archive, running from 24 January 2020 to 2 April 2020. In addition we use Zipf and Mandelbrot's power law to calibrate the extent to which they differ from normal language patterns. A context for the emails is provided by the recently revealed email trove of Dr. Fauci, obtained by Buzzfeed on 1 June 2021 obtained under the Freedom of Information Act. [ABSTRACT FROM AUTHOR]

As survey costs continue to rise and response rates decline, researchers are seeking more cost-effective ways to collect, analyze and process social and public opinion data. These issues have created an opportunity and interest in expanding the fit-for-purpose paradigm to include alternate sources such as passively collected sensor data and social media data. However, methods for accessing, sourcing and sampling social media data are just now being developed. In fact, there has been a small but growing body of literature focusing on comparing different Twitter data access methods through either the elaborate firehose or the free Twitter search or streaming APIs. Missing from the literature is a good understanding of how to randomly sample Tweets to produce datasets that are representative of the daily discourse, especially within geographical regions of interest, without requiring a census of all Tweets. This understanding is necessary for producing quality estimates of public opinion from social media sources such as Twitter. To address this gap, we propose and test the Velocity-Based Estimation for Sampling Tweets (VBEST) algorithm for selecting a probability based sample of tweets. We compare the performance of VBEST sample estimates to other methods of accessing Twitter through the Search API on the distribution of total Tweets as well as COVID-19 keyword incidence and frequency and find that the VBEST samples produce consistent and relatively low levels of overall bias compared to common methods of access through the Search API across many experimental conditions. [ABSTRACT FROM AUTHOR]

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. [ABSTRACT FROM AUTHOR]

This study sheds new light on how a hurricane affects spatial reactions and mobility across the US states based on Twitter data, whereas prior studies have only focused on the damaged region. First, this study finds that spatial reactions are differentiated by periods. For example, New York shows the second-highest reactions in the pre-hurricane weeks, North Carolina reveals the second-highest reactions in the hurricane weeks, and Texas exhibits the second-highest reactions in the post-hurricane weeks. This study also highlights that a hurricane plays a significant role in spatial displacements of the case study regions (Florida, North Carolina, and New York). To be specific, displacements in the hurricane weeks are 24 times higher than those in the pre-hurricane weeks. Lastly, this study finds that displacements within 5 km significantly increase, whereas those over 50 km significantly decrease in the hurricane weeks. [ABSTRACT FROM AUTHOR]

This work investigates empirically the impact of political party control over its candidates or vice versa on winning an election using a natural language processing technique called sentiment analysis (SA). To do this, a set of 7430 tweets bearing or related to #AnambraDecides2017 was streamed during the November 18, 2017, Anambra State gubernatorial election. These are Twitter discussions on the top five political parties and their candidates termed political actors in this paper. We conduct polarity and subjectivity sentiment analyses on all the tweets considering time as a useful dimension of SA. Furthermore, we use the word frequency to find words most associated with the political actors in a given time. We find most talked about topics using a topic modeling algorithm and how the computed sentiments and most frequent words are related to the topics per political actor. Among other things, we deduced from the experimental results that even though a political party serves as a platform that sales the personality of a candidate, the acceptance of the candidate/party adds to the winning of an election. For example, we found the winner of the election Willie Obiano benefiting from the values his party share among the people of the State. Associating his name with his party, All Progressive Grand Alliance (APGA) displays more positive sentiments and the subjective sentiment analysis indicates that Twitter users mentioning APGA are less emotionally subjective in their tweets than the other parties. [ABSTRACT FROM AUTHOR]

Clustering of tweets is useful for analyzing the attitudes of people towards a particular product. The companies can use this analysis to modify their products to meet the needs of people. Recently, K-means clustering is widely used to cluster the tweets with bag of words as a feature set. The key factors contributing to the quality of clusters and performance of clustering are dimensionality reduction and initial selection of centroids. This paper addresses these issues using a newly proposed Tag Score (T_S) model with improved K-means in which semantically similar features from bag of words are grouped into tags, scores are modified based on sentiment polarity values and the initial centroids are selected with the help of sentiment scores. The performance of the proposed T_S model with improved K-means is compared with T_S model with random K-means and conventional word vectors with random K-means by considering three labeled datasets and three unlabeled datasets. The results show that the proposed method produces significant results in approximately 70% of the cases in terms of purity, F-measure, intra-cluster distance and inter-cluster distance. [ABSTRACT FROM AUTHOR]

Language identification, as the task of determining the language a given text is written in, has progressed substantially in recent decades. However, three main issues remain still unresolved: (1) distinction of similar languages, (2) detection of multilingualism in a single document, and (3) identifying the language of short texts. In this paper, we describe our work on the development of a benchmark to encourage further research in these three directions, set forth an evaluation framework suitable for the task, and make a dataset of annotated tweets publicly available for research purposes. We also describe the shared task we organized to validate and assess the evaluation framework and dataset with systems submitted by seven different participants, and analyze the performance of these systems. The evaluation of the results submitted by the participants of the shared task helped us shed some light on the shortcomings of state-of-the-art language identification systems, and gives insight into the extent to which the brevity, multilingualism, and language similarity found in texts exacerbate the performance of language identifiers. Our dataset with nearly 35,000 tweets and the evaluation framework provide researchers and practitioners with suitable resources to further study the aforementioned issues on language identification within a common setting that enables to compare results with one another. [ABSTRACT FROM AUTHOR]

An experiment run in 2009 could not assess whether making monographs available in open access enhanced scholarly impact. This paper revisits the experiment, drawing on additional citation data and tweets. It attempts to answer the following research question: does open access have a positive influence on the number of citations and tweets a monograph receives, taking into account the influence of scholarly field and language? The correlation between monograph citations and tweets is also investigated. The number of citations and tweets measured in 2014 reveal a slight open access advantage, but the influence of language or subject should also be taken into account. However, Twitter usage and citation behaviour hardly overlap. [ABSTRACT FROM AUTHOR]

This study investigates the possibility of utilizing VGI in disaster management. Effective cross-jurisdictional disaster management requires real-time information, which is not available from official sources. This paper identifies tweets from Twitter as a potential VGI data source and shows how to discover and utilize relevant tweets. The paper proposes research methods for real-time (or near real-time) tweets harvesting, live tweets saving in a distributed geodatabase, and real-time VGI data redistribution. The study implements a Web GIS application as a platform for geo-tagged tweets operation. The implemented Web GIS application includes a tweet discovery component, a geo-tagged tweets mapping component, as well as an online geo-tagged tweets operation and analysis component. The major tasks include how to record the harvested geo-tagged tweets in a geodatabase so that it can be redistributed in real-time. Based on tweets from Hurricane Joaquin in 2015 and a hypothetical mass evacuation, the case study evaluates the pros and cons of VGI for response in emergency management. Spatial-temporal analysis components are also demonstrated. [ABSTRACT FROM AUTHOR]

With the global adoption of smart mobile devices equipped with localization capabilities and broad popularity of microblogging facilities like Twitter, the need for personal privacy has never been greater. This is especially so with computational and data processing infrastructures such as clouds that support big data analysis. Differential privacy of geospatially tagged data such as tweets can potentially ensure that degrees of location privacy can be preserved while allowing the information (tweet contents) to be used for research and analysis, e.g., sentiment analysis. In this paper, we evaluate differential location pattern-mining approaches considering both privacy and precision of geo-located tweets clustered according to Geo-Locations of Interest (GLI). We consider both the privacy protection strength and the accuracy of results, measuring the Euclidean distance between centroids of real GLIs and obfuscated ones, i.e., those incorporating privacy-preserving noise. We record the performance and sensitivity of the approach. We show how privacy and location precision are trade-offs, i.e., the higher the degree of privacy protection, the fewer the GLIs will be identified. We also quantify these trade-offs and their associated sensitivity levels. We illustrate the work through a big data case study on use of Twitter data for traffic-related data protection. [ABSTRACT FROM AUTHOR]

In the recent year, social networks have revolutionized the ways of interacting and exchanging information on the Internet. Millions of users interact frequently and share variety of digital content with each other. They express their feelings and opinions on every topic of interest. These opinions carry import value for personal, academic, and commercial applications, but the volume and the speed at which these are produced make it a challenging task for researchers and the underlying technologies to provide useful insights into such data. We attempt to extend the established online analytical processing (OLAP) technology to allow multidimensional analysis of social media data. In this paper, we pursue a goal of providing a generic multidimensional model dedicated to the OLAP of social media and specially Twitter. The proposed model reflects on some specifics such as recursive references between tweets, Empty dimension, and different types of hierarchies. It is implemented using NetBeans IDE platform. We present also some experimental results. We expect our proposed approach to be applicable for analyzing the data of other social networks as well. [ABSTRACT FROM AUTHOR]

Sentiment analysis is one of the effective techniques for mining the opinion from shapeless data contains text like review of the products, review of the movie. Sentiment analysis is used as a key to gather response from consumers, reviews of brands, marketing analyses, and political campaigns. In the subject of natural processing, performing sentiment analysis using the data obtained from Twitter is considered as a new study in these days. The dataset is gathered using the Twitter API and the Twitter package. The analysis of Twitter data is a process which takes place automatically by text data analysis to determine the view of public on the specified topic. Here, an improvised sentimental analysis model is proposed to identify the polarity of the tweets such as positive, neutral and negative. In this paper, stochastic gradient descent (SGD) algorithm uses stochastic gradient neural network (SGNN) to categorize the sentiment analysis on basis of tweets provided by the Twitter users and the proposed stochastic gradient descent optimization Algorithm based on stochastic gradient neural network (SGDOA-SGNN) provides better performance when compared with the existing Forest-Whale Optimization Algorithm based on deep neural network F-WOA-DNN model., Competing Interests: Conflict of interestOn behalf of all authors, the corresponding author states that there is no conflict of interest., (© The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd 2023, Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.)

In this paper, we propose and apply a method to analyze the activeness of an event based on related tweets. The method characterizes and measures activeness of an event by a set of indicators. The indicators proposed in this paper are original tweet count, retweet count, follower count, positive sentiment, negative sentiment, daily change in users count, and sparseness of user community. We present procedures to compute the last two indicators. All indicators collectively are used to determine the activeness of an event. This approach is used to analyze the Syrian-refugee-crisis-related tweets. Its generality is demonstrated by applying it to analyze "immigration"-related tweets. [ABSTRACT FROM AUTHOR]