Monitoring event-driven dynamics on Twitter: a case study in Belarus.
Ontology highlight
ABSTRACT: Supplementary information
The online version contains supplementary material available at 10.1007/s43545-022-00330-x.
SUBMITTER: Rice NM
PROVIDER: S-EPMC8990676 | biostudies-literature | 2022
REPOSITORIES: biostudies-literature
Publications
Monitoring event-driven dynamics on Twitter: a case study in Belarus.
Rice Natalie M NM Horne Benjamin D BD Luther Catherine A CA Borycz Joshua D JD Allard Suzie L SL Ruck Damian J DJ Fitzgerald Michael M Manaev Oleg O Prins Brandon C BC Taylor Maureen M Bentley R Alexander RA
SN social sciences 20220408 4
Analysts of social media differ in their emphasis on the effects of message content versus social network structure. The balance of these factors may change substantially across time. When a major event occurs, initial independent reactions may give way to more social diffusion of interpretations of the event among different communities, including those committed to disinformation. Here, we explore these dynamics through a case study analysis of the Russian-language Twitter content emerging from ...[more]
Similar Datasets
Project description:The current COVID-19 pandemic has profoundly impacted people's lifestyles and travel behaviours, which may persist post-pandemic. An effective monitoring tool that allows us to track the level of change is vital for controlling viral transmission, predicting travel and activity demand and, in the long term, for economic recovery. In this paper, we propose a set of Twitter mobility indices to explore and visualise changes in people's travel and activity patterns, demonstrated through a case study of London. We collected over 2.3 million geotagged tweets in the Great London Area (GLA) from Jan 2019 -Feb 2021. From these, we extracted daily trips, origin-destination matrices, and spatial networks. Mobility indices were computed based on these, with the year 2019 as a pre-Covid baseline. We found that in London, (1) People are making fewer but longer trips since March 2020. (2) In 2020, travellers showed comparatively reduced interest in central and sub-central activity locations compared to those in outer areas, whereas, in 2021, there is a sign of a return to the old norm. (3) Contrary to some relevant literature on mobility and virus transmission, we found a poor spatial relationship at the Middle Layer Super Output Area (MSOA) level between reported COVID-19 cases and Twitter mobility. It indicated that daily trips detected from geotweets and their most likely associated social, exercise and commercial activities are not critical causes for disease transmission in London. Aware of the data limitations, we also discuss the representativeness of Twitter mobility by comparing our proposed measures to more established mobility indices. Overall, we conclude that mobility patterns obtained from geo-tweets are valuable for continuously monitoring urban changes at a fine spatiotemporal scale.
| S-EPMC10132666 | biostudies-literature
Project description:BackgroundTraditional monitoring for adverse events following immunization (AEFI) relies on various established reporting systems, where there is inevitable lag between an AEFI occurring and its potential reporting and subsequent processing of reports. AEFI safety signal detection strives to detect AEFI as early as possible, ideally close to real time. Monitoring social media data holds promise as a resource for this.ObjectiveThe primary aim of this study is to investigate the utility of monitoring social media for gaining early insights into vaccine safety issues, by extracting vaccine adverse event mentions (VAEMs) from Twitter, using natural language processing techniques. The secondary aims are to document the natural language processing techniques used and identify the most effective of them for identifying tweets that contain VAEM, with a view to define an approach that might be applicable to other similar social media surveillance tasks.MethodsA VAEM-Mine method was developed that combines topic modeling with classification techniques to extract maximal VAEM posts from a vaccine-related Twitter stream, with high degree of confidence. The approach does not require a targeted search for specific vaccine reaction-indicative words, but instead, identifies VAEM posts according to their language structure.ResultsThe VAEM-Mine method isolated 8992 VAEMs from 811,010 vaccine-related Twitter posts and achieved an F1 score of 0.91 in the classification phase.ConclusionsSocial media can assist with the detection of vaccine safety signals as a valuable complementary source for monitoring mentions of vaccine adverse events. A social media-based VAEM data stream can be assessed for changes to detect possible emerging vaccine safety signals, helping to address the well-recognized limitations of passive reporting systems, including lack of timeliness and underreporting.
| S-EPMC9247809 | biostudies-literature
Project description:BackgroundSocial media technology such as Twitter allows users to share their thoughts, feelings, and opinions online. The growing body of social media data is becoming a central part of infodemiology research as these data can be combined with other public health datasets (eg, physical activity levels) to provide real-time monitoring of psychological and behavior outcomes that inform health behaviors. Currently, it is unclear whether Twitter data can be used to monitor physical activity levels.ObjectiveThe aim of this study was to establish the feasibility of using Twitter data to monitor physical activity levels by assessing whether the frequency and sentiment of physical activity-related tweets were associated with physical activity levels across the United States.MethodsTweets were collected from Twitter's application programming interface (API) between January 10, 2017 and January 2, 2018. We used Twitter's garden hose method of collecting tweets, which provided a random sample of approximately 1% of all tweets with location metadata falling within the United States. Geotagged tweets were filtered. A list of physical activity-related hashtags was collected and used to further classify these geolocated tweets. Twitter data were merged with physical activity data collected as part of the Behavioral Risk Factor Surveillance System. Multiple linear regression models were fit to assess the relationship between physical activity-related tweets and physical activity levels by county while controlling for population and socioeconomic status measures.ResultsDuring the study period, 442,959,789 unique tweets were collected, of which 64,005,336 (14.44%) were geotagged with latitude and longitude coordinates. Aggregated data were obtained for a total of 3138 counties in the United States. The mean county-level percentage of physically active individuals was 74.05% (SD 5.2) and 75.30% (SD 4.96) after adjusting for age. The model showed that the percentage of physical activity-related tweets was significantly associated with physical activity levels (beta=.11; SE 0.2; P<.001) and age-adjusted physical activity (beta=.10; SE 0.20; P<.001) on a county level while adjusting for both Gini index and education level. However, the overall explained variance of the model was low (R2=.11). The sentiment of the physical activity-related tweets was not a significant predictor of physical activity level and age-adjusted physical activity on a county level after including the Gini index and education level in the model (P>.05).ConclusionsSocial media data may be a valuable tool for public health organizations to monitor physical activity levels, as it can overcome the time lag in the reporting of physical activity epidemiology data faced by traditional research methods (eg, surveys and observational studies). Consequently, this tool may have the potential to help public health organizations better mobilize and target physical activity interventions.
| S-EPMC6682305 | biostudies-literature
Project description:Due to its asynchronous message-sharing and real-time capabilities, Twitter offers a valuable opportunity to detect events in a timely manner. Existing approaches for event detection have mainly focused on building a temporal profile of named entities and detecting unusually large bursts in their usage to signify an event. We extend this line of research by incorporating external knowledge bases such as DBPedia, WordNet; and exploiting specific features of Twitter for efficient event detection. We show that our system utilizing temporal, social, and Twitter-specific features yields improvement in the precision, recall, and DERate on the benchmarked Events2012 corpus compared to the state-of-the-art approaches.
| S-EPMC7274331 | biostudies-literature
Project description:The rise of global value chains (GCVs) has seen the transfer of carbon emissions embodied in every step of international trade. Building a coordinated, inclusive and green GCV can be an effective and efficient way to achieve carbon emissions mitigation targets for countries that participate highly in GCVs. In this paper, we first describe the energy consumption as well as the territorial and consumption-based carbon emissions of Belarus and its regions from 2010 to 2017. The results show that Belarus has a relatively clean energy structure with 75% of Belarus' energy consumption coming from imported natural gas. The 'chemical, rubber and plastic products' sector has expanded significantly over the past few years; its territorial-based emissions increased 10-fold from 2011 to 2014, with the 'food processing' sector displaying the largest increase in consumption-based emissions. An analysis of regional emissions accounts shows that there is significant regional heterogeneity in Belarus with Mogilev, Gomel and Vitebsk having more energy-intensive manufacturing industries. We then analysed the changes in Belarus' international trade as well as its emission impacts. The results show that Belarus has changed from a net carbon exporter in 2011 to a net carbon importer in 2014. Countries along the Belt and Road Initiative, such as Russia, China, Ukraine, Poland and Kazakhstan, are the main trading partners and carbon emission importers/exporters for Belarus. 'Construction' and 'chemical, rubber and plastic products' are two major emission-importing sectors in Belarus, while 'electricity' and 'ferrous metals' are the primary emission-exporting sectors. Possible low-carbon development pathways are discussed for Belarus through the perspectives of global supply and the value chain.
| S-EPMC7426056 | biostudies-literature
Project description:Sensory neurons generate spike patterns upon receiving external stimuli and encode key information to the spike patterns, enabling energy-efficient external information processing. Herein, we report an epifluidic electronic patch with spiking sweat clearance using a sensor containing a vertical sweat-collecting channel for event-driven, energy-efficient, long-term wireless monitoring of epidermal perspiration dynamics. Our sweat sensor contains nanomesh electrodes on its inner wall of the channel and unique sweat-clearing structures. During perspiration, repeated filling and abrupt emptying of the vertical sweat-collecting channel generate electrical spike patterns with the sweat rate and ionic conductivity proportional to the spike frequency and amplitude over a wide dynamic range and long time (> 8 h). With such 'spiking' sweat clearance and corresponding electronic spike patterns, the epifluidic wireless patch successfully decodes epidermal perspiration dynamics in an event-driven manner at different skin locations during exercise, consuming less than 0.6% of the energy required for continuous data transmission. Our patch could integrate various on-skin sensors and emerging edge computing technologies for energy-efficient, intelligent digital healthcare.
| S-EPMC9640696 | biostudies-literature
Project description:News event monitoring systems allow real-time monitoring of a large number of events reported in the news, including the urgent and critical events comprising the so-called hard news. These systems heavily rely on natural language processing (NLP) to perform automatic event extraction at scale. While state-of-the-art event extraction models are readily available, integrating them into a news event monitoring system is not as straightforward as it seems due to practical issues related to model selection, robustness, and scale. To address this gap, we present a study on the practical use of event extraction models for news event monitoring. Our study focuses on the key task of closed-domain main event extraction (CDMEE), which aims to determine the type of the story's main event and extract its arguments from the text. We evaluate a range of state-of-the-art NLP models for this task, including those based on pre-trained language models. Aiming at a more realistic evaluation than done in the literature, we introduce a new dataset manually labeled with event types and their arguments. Additionally, we assess the scalability of CDMEE models and analyze the trade-off between accuracy and inference speed. Our results give insights into the performance of state-of-the-art NLP models on the CDMEE task and provide recommendations for developing effective, robust, and scalable news event monitoring systems.
| S-EPMC11623237 | biostudies-literature
Project description:BackgroundIn response to growing anti-vaccine activism on social media, the #DoctorsSpeakUp event was designed to promote pro-vaccine advocacy. This study aimed to analyze Twitter content related to the event to determine (1) characteristics of the Twitter users who authored these tweets, (2) the proportion of tweets expressing pro-vaccine compared to anti-vaccine sentiment, and (3) the content of these tweets.MethodsData were collected using Twitter's Filtered Streams Interface, and included all publicly available tweets with the "#DoctorsSpeakUp" hashtag on March 5, 2020, the day of the event. Two independent coders assessed a 5% subsample of original tweets (n = 966) using a thematic content analysis approach. Cohen's κ ranged 0.71-1.00 for all categories. Chi-square and Fisher's exact tests were used to examine associations between tweet sentiment, type of account, and tweet content (personal narrative and/or statement about research or science). Accounts were analyzed for likelihood of being a bot (i.e. automated account) using Botometer.ResultsOf 847 (87.7%) relevant tweets, 244 (28.8%) were authored by a Twitter user that identified as a parent and 68 (8.0%) by a user that identified as a health professional. With regard to sentiment, 167 (19.7%) were coded as pro-vaccine and 668 (78.9%) were coded as anti-vaccine. Tweet sentiment was significantly associated with type of account (p < 0.001) and tweet content (p = 0.001). Of the 575 unique users in our dataset, 31 (5.4%) were classified as bots using Botometer.ConclusionsOur results suggest a highly coordinated response of devoted anti-vaccine antagonists in response to the #DoctorsSpeakUp event. These findings can be used to help vaccine advocates leverage social media more effectively to promote vaccines. Specifically, it would be valuable to ensure that pro-vaccine messages consider hashtag use and pre-develop messages that can be launched and promoted by pro-vaccine advocates.
| S-EPMC9351384 | biostudies-literature
Project description:In this study, we utilize Protein Residue Networks (PRNs), constructed using Local Spatial Pattern (LSP) alignment, to explore the dynamic behavior of Catabolite Activator Protein (CAP) upon the sequential binding of cAMP. We employed the Degree Centrality of these PRNs to investigate protein dynamics on a sub-nanosecond time scale, hypothesizing that it would reflect changes in CAP's entropy related to its thermal motions. We show that the binding of the first cAMP led to an increase in stability in the Cyclic-Nucleotide Binding Domain A (CNBD-A) and destabilization in CNBD-B, agreeing with previous reports explaining the negative cooperativity of cAMP binding in terms of an entropy-driven allostery. LSP-based PRNs also allow for the study of Betweenness Centrality, another graph-theoretical characteristic of PRNs, providing insights into global residue connectivity within CAP. Using this approach, we were able to correctly identify amino acids that were shown to be critical in mediating allosteric interactions in CAP. The agreement between our studies and previous experimental reports validates our method, particularly with respect to the reliability of Degree Centrality as a proxy for entropy related to protein thermal dynamics. Because LSP-based PRNs can be easily extended to include dynamics of small organic molecules, polynucleotides, or other allosteric proteins, the methods presented here mark a significant advancement in the field, positioning them as vital tools for a fast, cost-effective, and accurate analysis of entropy-driven allostery and identification of allosteric hotspots.
| S-EPMC10851786 | biostudies-literature
Project description:BackgroundThe COVID-19 pandemic has affected people's daily lives and has caused economic loss worldwide. Anecdotal evidence suggests that the pandemic has increased depression levels among the population. However, systematic studies of depression detection and monitoring during the pandemic are lacking.ObjectiveThis study aims to develop a method to create a large-scale depression user data set in an automatic fashion so that the method is scalable and can be adapted to future events; verify the effectiveness of transformer-based deep learning language models in identifying depression users from their everyday language; examine psychological text features' importance when used in depression classification; and, finally, use the model for monitoring the fluctuation of depression levels of different groups as the disease propagates.MethodsTo study this subject, we designed an effective regular expression-based search method and created the largest English Twitter depression data set containing 2575 distinct identified users with depression and their past tweets. To examine the effect of depression on people's Twitter language, we trained three transformer-based depression classification models on the data set, evaluated their performance with progressively increased training sizes, and compared the model's tweet chunk-level and user-level performances. Furthermore, inspired by psychological studies, we created a fusion classifier that combines deep learning model scores with psychological text features and users' demographic information, and investigated these features' relations to depression signals. Finally, we demonstrated our model's capability of monitoring both group-level and population-level depression trends by presenting two of its applications during the COVID-19 pandemic.ResultsOur fusion model demonstrated an accuracy of 78.9% on a test set containing 446 people, half of which were identified as having depression. Conscientiousness, neuroticism, appearance of first person pronouns, talking about biological processes such as eat and sleep, talking about power, and exhibiting sadness were shown to be important features in depression classification. Further, when used for monitoring the depression trend, our model showed that depressive users, in general, responded to the pandemic later than the control group based on their tweets (n=500). It was also shown that three US states-New York, California, and Florida-shared a similar depression trend as the whole US population (n=9050). When compared to New York and California, people in Florida demonstrated a substantially lower level of depression.ConclusionsThis study proposes an efficient method that can be used to analyze the depression level of different groups of people on Twitter. We hope this study can raise awareness among researchers and the public of COVID-19's impact on people's mental health. The noninvasive monitoring system can also be readily adapted to other big events besides COVID-19 and can be useful during future outbreaks.
| S-EPMC8330892 | biostudies-literature