cord-018558-cw9ls112	2016	
cord-018619-aknktp6d	2015	
cord-024385-peakgsyp	2020	
cord-026173-3a512flu	2020	
cord-026935-586w2cam	2020	
cord-027431-6twmcitu	2020	
cord-029501-syp9ca7t	2020	
cord-032750-sjsju0qp	2020	title: Navigating ''Home Schooling'' during COVID-19: Australian public response on Twitter Choice to send children to school lies with families, and distance education packages and resources or online remote learning will be provided to any student who is kept home. Parents can choose not to send their children to school, but are then ''responsible for the student''s learning, safety and wellbeing at home or elsewhere''. We adopt both quantitative (descriptive) and qualitative approaches to analysing the contents of the collected tweets to identify their major themes and concerns of the Australian public in relation to home schooling during the pandemic. Arguably, the frustration over the definition of the learning is highlighting how unsure parents feel in this new role: I came across some online twitter debate on whether it was technically home schooling when in reality you aren''t setting the work.
cord-034814-flp6s0wd	2020	
cord-035254-630w2rtn	2020	
cord-102236-z0408dje	2020	
cord-121200-2qys8j4u	2020	While many previous works have largely studied the problem on a small-scale by assuming uni-modality of data which may not give us faithful results, we propose a novel scalable hybrid model that combines Bidirectional Gated Recurrent Units (BiGRUs) and Convolutional Neural Networks to detect depressed users on social media such as Twitter-based on multi-modal features. To be specific, this work aims to develop a new novel deep learning-based solution for improving depression detection by utilizing multi-modal features from diverse behaviour of the depressed user in social media. To this end, we propose a hybrid model comprising Bidirectional Gated Recurrent Unit (BiGRU) and Conventional Neural network (CNN) model to boost the classification of depressed users using multi-modal features and word embedding features. The most closely related recent work to ours is [23] where the authors propose a CNN-based deep learning model to classify Twitter users based on depression using multi-modal features.
cord-123103-pnjt9aa4	2020	
cord-125817-5o12mbut	2020	title: Open access institutional and news media tweet dataset for COVID-19 social science research On the past Ebola epidemic crisis, scholars found the importance of using Twitter data to do social science research [3] , [4] , many of them use this microblog data as social indicators to analyze the effect of epidemic outbreak on public concerns [5] , health information needs and health seeking behavior [6] , and public response to policy makers [7] etc. Current open access COVID-19 Twitter data were mainly collected by keywords, such as coronavirus, Covid-19 etc [8] , [9] , none of the them is dedicated to government/news media tweet collection. Given that our retrieval targets are policy makers and news source, we believe our dataset can provide scholars more valuable data to conduct social science research in related fields, such as crisis communication, public relation etc. https://github.com/narcisoyu/Institional-and-news-media-tweet-dataset-for-COVID-19social-science-research.
cord-131667-zl5txjqx	2020	
cord-135784-ad5avzd6	2020	
cord-156676-wes5my9e	2020	
cord-164516-qp7k5fz9	2020	
cord-169484-mjtlhh5e	2020	To track online emotional expressions of the Austrian population close to real-time during the COVID-19 pandemic, we build a self-updating monitor of emotion dynamics using digital traces from three different data sources. The interactive dashboard showcasing our data is available online under http://www.mpellert.at/covid19_monitor_austria/. We gather these data in the form of text from platforms such as Twitter and news forums, where large groups of users discuss timely issues. To fill a gap, we build a dashboard with processed data from three different sources to track the sentiment in Austrian social media during COVID-19. In addition, measures that strongly affect people''s daily lives over a long period of time, as well as high level of uncertainty, likely contribute to the unprecedented changes of collective emotional expression in online social media.
cord-180457-047iqerh	2020	
cord-180835-sgu7ayvw	2020	
cord-186031-b1f9wtfn	2020	
cord-207180-k6f6cmyn	2020	
cord-208179-9pwjnrgl	2020	COVID-19 has given rise to malicious content online, including online abuse and hate toward British MPs. In order to understand and contextualise the level of abuse MPs receive, we consider how ministers use social media to communicate about the crisis, and the citizen engagement that this generates. However the correlation is significant across the sample of all MPs. The reaction of the public to the Conservative party and the government''s actions during COVID-19 may be related to the conditions of a public health crisis as discussed in [58, 39] , in which citizens may feel more motivated to trust authorities, although it may also follow from the crisis engaging a different group of people than usually respond to politicians on Twitter. Our third research question asked: Which social media activities of UK MPs during the COVID-19 pandemic receive the most abusive replies?
cord-209697-bfc4h4b3	2020	We first manually group the hashtags into six main categories, namely, 1) General COVID, 2) Quarantine, 3) Panic Buying, 4) School Closures, 5) Lockdowns, and 6) Frustration and Hope}, and study the temporal evolution of tweets in these hashtags. We adopt a state-of-the-art semantic role labeling approach to identify the action words and then leverage a LSTM-based dependency parsing model to analyze the context of action words (e.g., verb deal is accompanied by nouns such as anxiety, stress, and crisis). We group the hashtags into six main categories, namely 1) General COVID, 2) Quarantine, 3) School Closures, 4) Panic Buying, 5) Lockdowns, and 6) Frustration and Hope to quantitatively and qualitatively understand the chain of events. We develop a Seeded LDA model to categorize tweets into the five hashtag groups: i) General COVID, ii) School Closures, iii) Panic Buying, iv) Lockdowns, and v) Quarantine by seeding each group with seed words from our analysis in Section III-B.
cord-211410-7r2xx73n	2020	
cord-217856-4pd1mamv	2020	
cord-225177-f7i0sbwt	2020	
cord-225887-kr9uljop	2020	
cord-227156-uy4dykhg	2020	
cord-235946-6vu34vce	2020	
cord-252344-5a0sriq9	2020	
cord-265704-g3iish7x	2020	
cord-269093-x6taxwkx	2019	However, very few review studies have undertaken grouping according to similarities and differences to predict the personality and behavior of individuals with the help of social networking sites such as Facebook, Twitter, and Instagram. However, most of the studies have been done on Twitter, as it is more popular and newer than Facebook and Instagram particularly from 2015 to 2017, and more research needs to be done on other social media spheres in order to analyze the trending behaviors of users. The result section includes a table which provides the research paper analysis according to the year along with pie chart figures, data collection, and behavior analysis methods and classifications based on different methods with line graphs [9] . The results section includes the percentage of research on the three social networking sites, research papers according to year with bar graph representations, data collection and behavior analysis methods and classification based on the different methods with line graph representations.
cord-278119-8k2j3kjv	2020	From these searches, we determined the magnitude and time course of Twitter activity then coded this activity into content that promoted or refuted a SMT/immunity link. In this descriptive study, we detail how Twitter activity can be used to not only document the magnitude and time course of misinformation describing a link between spinal manipulative therapy (SMT) and boosting immunity, but how social media activity promotes or refutes these claims. These data suggest that the majority of twitter activity regarding a SMT/immunity link is associated with the chiropractic profession with the total number of posts being roughly equal between those promoting and those refuting this link. Direct Twitter activity (posts, likes, retweets, engagement) was similar between tweets promoting and refuting a SMT/immunity link.
cord-281145-pxzsph5v	2020	When it comes to using Twitter data for drug identification and pharmacovigilance tasks, authors of works like [7] [8] [9] have been consistently releasing publicly available datasets, software tools, and complete Natural Language Processing (NLP) systems with their works. In an attempt to shift the biomedical community into better practices for research transparency and reproducibility, we introduce the Social Media Mining Toolkit (SMMT), a suite of tools aimed to encapsulate the cumbersome details of acquiring, preprocessing, annotating, and standardizing social media data. The need for a toolkit like SMMT arose from our work using Twitter data for the characterization of disease transmission during natural disasters [10] and mining large-scale repositories for drug usage related tweets for pharmacovigilance purposes [11] . After preprocessing the acquired social media data, researchers have the capabilities of standardizing their tweets'' text with our set of tools.
cord-285522-3gv6469y	2015	Big data has become an important issue for a large number of research areas such as data mining, machine learning, computational intelligence, information fusion, the semantic Web, and social networks. The rise of different big data frameworks such as Apache Hadoop and, more recently, Spark, for massive data processing based on the MapReduce paradigm has allowed for the efficient utilisation of data mining methods and machine learning algorithms in different domains. Currently, the exponential growth of social media has created serious problems for traditional data analysis algorithms and techniques (such as data mining, statistics, machine learning, and so on) due to their high computational complexity for large datasets. This section provides a description of the basic methods and algorithms related to network analytics, community detection, text analysis, information diffusion, and information fusion, which are the areas currently used to analyse and process information from social-based sources.
cord-287703-1shbiee5	2020	The use of hashtags at medical conferences allows material to be discussed and improved on by the experts via online conversation on Twitter. CONCLUSION: Twitter #AAST 2016–2019 online engagement and interactions have declined during the last 4 years while impressions have grown steadily indicating potential widespread dissemination of trauma-related knowledge and evidence-based practices, and increased online utilization of conference material to trauma surgeons, residents and fellows, trauma scientists, other physicians and the lay public. Though tweets and retweets declined, impressions increased significantly from 2016 to 2019, from 5.8 million to 10 million (p<0.05), potentially indicating contents from AAST conference presentations were still being widely viewed and disseminated. Twitter #AAST 2016-2019 online engagement and interactions have declined during the last 4 years while impressions have grown steadily indicating potential widespread dissemination of trauma-related knowledge and evidence-based practices, and increased online utilization of conference material to trauma surgeons, fellows, residents, trauma scientists, other physicians and the lay public.
cord-288195-3lcs77uf	2020	
cord-297462-c5hafan8	2018	METHOD: This study examined how the public discussed measles during the measles outbreak in the United States during early 2015 that originated in Disneyland Park in Anaheim, CA, through a semantic network analysis of the content of around 1 million tweets using KH coder. 3 This study adds to the research on crisis and emergency risk communication by demonstrating that social media users applied different frames to understand the public health crisis associated with a measles outbreak: news update frame, public health frame, vaccination frame, and political frame. Practically, the findings of the study allow public health professionals to understand how social media users make sense of an EID during different stages of the outbreak so that they can develop more effective crisis communication strategies.
cord-299982-plw0dukq	2020	
cord-302411-unoiwi4g	2020	
cord-303506-rqerh2u3	2020	
cord-309790-rx9cux8i	2020	
cord-311906-i5i0clgq	2020	
cord-315647-isjacgq1	2020	Objective: The aim of this study is to identify the most common symptoms reported by covid-19 patients in the Arabic language and order the symptoms appearance based on the collected data. For example, Twitter has been the source for data for many health and medical studies; such as surveillance and monitoring of Flu and Cancer timeline and distribution across the USA using Twitter [1] , analyzing the spread of influenza in the UAE based on geotagged Arabic Tweets [2] , surveillance and monitoring of Influenza in the UAE based on Arabic and English tweets [3] , identifying symptoms and disease in Saudi Arabia using Twitter [4] , and most recently on analyzing COVID-19 symptoms on Twitter [5] and analyzing the chronological and geographical distribution of COVID-19 infected tweeters in the USA [6] . Initially, we shuffled Arabic tweets and searching for tweets with COVID-19 symptoms and also collected tweets for users who reported themselves infected through clinical test.
cord-320208-uih4jf8w	2020	In this article, we propose a CorExQ9 algorithm that integrates a Correlation Explanation (CorEx) learning algorithm and clinical Patient Health Questionnaire (PHQ) lexicon to detect COVID-19 related stress symptoms at a spatiotemporal scale in the United States. In this article, we propose a CorExQ9 algorithm that integrates Correlation Explanation (CorEx) learning algorithm and clinical PHQ lexicon to detect COVID-19 related stress symptoms at a spatiotemporal scale in the United States. We assessed the level of stress expressed in COVID-19 related tweets by integrating a lexicon-based method derived from established clinical assessment questionnaire PHQ-9 [46] . The CorEx algorithm combined with clinical stress measure index (PHQ-9) helped to minimize human interventions and human language ambiguity in social media data mining for stress detection and provided accurate stress symptom measures of Twitter users related to the COVID-19 pandemic.
cord-328461-3r5vycnr	2020	
cord-329999-flzqm3wh	2020	Four studies (total N = 2,634) explored the effect of message attributes (authoritativeness of source, consensus indicators), viewer characteristics (digital literacy, personality, and demographic variables) and their interaction (consistency between message and recipient beliefs) on self-reported likelihood of spreading examples of disinformation. Descriptive statistics for participant characteristics (personality, conservatism, new media literacy and age) and their reactions to the stimuli (likelihood of sharing, belief the stories were likely to be true, and rating of likelihood that they had seen them before) are summarised in Table 2 . This evaluated the extent to which digital media literacy (NMLS), authority of the message source, consensus, belief in veracity of the messages, consistency with participant beliefs (operationalised as the total SECS conservatism scale score), age and personality (Extraversion, Conscientiousness, Agreeableness, Openness to Experience and Neuroticism), predicted self-rated likelihood of sharing the posts.
cord-334574-1gd9sz4z	2020	
cord-344832-0ah4w59o	2020	For future disaster preparedness, we argue that the municipal government, as a responsible agent, should (1) make available instructional information in foreign languages on social media, (2) transfer such information through collaboration with transmitters, and (3) examine the use of local hashtags in social media to strengthen non-Japanese speaker''s capacity to adapt. We regard disaster resilience in the information ecology framework to encompass the efforts of collaboration and communication dependencies that exist amongst stakeholders engaged in the situation within a local context. In this review, social media emerges as a new trend in technology and rather becomes the medium for sharing information with the aim to reduce anxiety about a disaster situation that could negatively affect the people involved [36] . These cases suggest that social media promote effective resilience in communication, and that the delivery of information to foreigners in Japan from different language backgrounds and cultures further creates traits where personal connection contributes to information accessibility choices.
cord-347459-8ju196uu	2020	Moreover, in terms of the impact of tweets, as measured by the rate at which they are retweeted, followers were more likely to ''spread the word'' when the tweet was content-rich (discussed a crime specific matter and contained media), and account holders were themselves more active on Twitter. The analysis of 114,257 tweets and their metadata indicate that (a) most of the tweets focused on issues that were not specifically about crime; (b) during the time of crisis the stakeholders in question tended to increase their retweeting activity rather than creating original tweets; (c) the visibility of an account (number of followers and favouriting habits) and the richness of the content (discussing Covid-19, crime specific issues and including media such as images) were associated with the likelihood of messages spreading (both in terms of whether they were retweeted and the frequency with which this was so); (d) relative to the preceding 5 months, during the first 5 months of the pandemic tweets on Fraud, Cybercrime and Domestic abuse increased significantly.
cord-349898-nvi8h77t	2020	
cord-356353-e6jb0sex	2020	Both practices rely upon and reinforce a pervasive appetite for digital input or feedback that we characterize as "data hunger." They also share a propensity to assemble insight and make meaning accretively-a propensity that we denote here as "world or meaning accretion." Throughout this article, we probe the dynamic interaction of social and machine learning by drawing examples from one genre of online social contention and connection in which the pervasive influence of machine learning is evident: namely, that which occurs across social media channels and platforms. In such settings, the data accretion upon which machine learning depends for the development of granular insights-and, on social media platforms, associated auctioning and targeting of advertising-compounds the cumulative, sedimentary effect of social data, making negative impressions generated by "revenge porn," or by one''s online identity having been fraudulently coopted, hard to displace or renew.