Redes Sociales Geolocalizadas Y Covid-19: Analisis De La Actividad Espaciotemporal De Los Usuarios De Twitter De Espana Durante La Pandemia

This work seeks to show Twitter as an alternative data source for the study of the pandemic caused by the COVID-19 virus in Spain. For this work, an analysis of the spatial and temporal distribution of the sample of users obtained in three different periods of the year 2020 is proposed, and then the obtained results are compared with the same periods of the year prior to the pandemic. A space-time analysis of the use of terms associated with the disease is also elaborated, and heat maps are made to observe the impact caused in the activity of two cities of relevant tourist weight. The obtained results indicate a sharp decrease in the number of users who publish geolocated tweets in the country throughout 2020, especially in the second half of the year and in the interior provinces of the peninsula. A less pronounced decrease in the number of users is also observed in coastal areas and provinces oriented to the tourism sector.

Spatiotemporal analysis of retail: pre- and post-COVID dynamics in Gros, San Sebastian

The decrease of commercial activity that has been occurring in the last decade has recently accentuated by the COVID pandemic, affecting the livability of cities and public space. This paper analyzes the ground floor activities in Gros neighbourhood, in San Sebastian, Spain, observing both its temporal evolution and its spatial distribution. The study performs two in situ geolocation data collections in January and August 2020, immediately before and after the COVID lockdown in Spain. Through the collected data, it analyzes the distribution and evolution of ground floor space dedicated to public activities. The study concludes that the activities suffered a decrease of 1.8% in the analyzed period, and that activities located on pedestrianized streets or with fewer lanes have had fewer closures. The work also shows which efforts are needed for in situ data collection to guide urban policy. © 2022 Prensas de la Universidad de Zaragoza. All rights reserved.

Learning from a Distance: Assessing the impact of the Pandemic through a Virtual Reference Service

With the onslaught of the global COVID19 pandemic, universities were forced to quickly pivot to exclusively remote and virtual service options. To further complicate the situation, many international student populations at these institutions were forced to study remotely in their home countries due to the pandemic and visa restrictions. In Canada and Ontario, International students make up a major revenue source for post-secondary institutions, making the need to find viable solutions to continue to serve these populations essential to their financial stability. The Ontario Council of University Libraries (OCUL) runs a shared virtual reference service called Ask a Librarian (Ask). This paper assessed the global pandemic's impact through a comparative study of the service before, during, and after the pandemic's height. Using IP addresses, this study evaluated the impact of geographical location on the user's access to virtual library resources, as well as identified any barriers, shifts, or trends in the service. The COVID-19 pandemic has changed the face of education and remote learning indefinitely. The hope of this study is to assess the overall success and pitfalls of our current virtual reference services and suggest future improvement areas. © 2023 Association of Canadian Map Libraries and Archives. All rights reserved.

COVID-19 Vaccine Hesitancy: Analysing Twitter to Identify Barriers to Vaccination in a Low Uptake Region of the UK.

To facilitate effective targeted COVID-19 vaccination strategies, it is important to understand reasons for vaccine hesitancy where uptake is low. Artificial intelligence (AI) techniques offer an opportunity for real-time analysis of public attitudes, sentiments, and key discussion topics from sources of soft-intelligence, including social media data. In this work, we explore the value of soft-intelligence, leveraged using AI, as an evidence source to support public health research. As a case study, we deployed a natural language processing (NLP) platform to rapidly identify and analyse key barriers to vaccine uptake from a collection of geo-located tweets from London, UK. We developed a search strategy to capture COVID-19 vaccine related tweets, identifying 91,473 tweets between 30 November 2020 and 15 August 2021. The platform's algorithm clustered tweets according to their topic and sentiment, from which we extracted 913 tweets from the top 12 negative sentiment topic clusters. These tweets were extracted for further qualitative analysis. We identified safety concerns; mistrust of government and pharmaceutical companies; and accessibility issues as key barriers limiting vaccine uptake. Our analysis also revealed widespread sharing of vaccine misinformation amongst Twitter users. This study further demonstrates that there is promising utility for using off-the-shelf NLP tools to leverage insights from social media data to support public health research. Future work to examine where this type of work might be integrated as part of a mixed-methods research approach to support local and national decision making is suggested.

Implementation of Haversine Algorithm and Geolocation for travel recommendations on Smart Applications for Backpackers in Bali

Bali is one of the islands known as a tourist destination with the main purpose of traveling to Bali to enjoy the beauty of nature. Various tourist activities in Bali are well known both nationally and internationally. With so many types of tours available in Bali, travelers, especially first-time visitors, may need a guide on the tourist attractions they want to visit in Bali. However, some tourists, especially backpackers, backpackers are known to explore tourist attractions independently, freely, and with as little budget as possible. Concerning this statement and the decline in tourists to Bali due to the impact of the Covid-19 pandemic, the author decided to use the Haversine formula to develop a geographic information system for smart backpacker travel recommendations. with this problem. This Android application helps tourists travel from registration to tour guides. Implementing the Haversine formula in your app is equivalent to up to 88% of the distance reported by the Google Maps API. These results are used as a recommendation function for the selection of attractions by showing the distance between the previous backpacker's location selection and attractions. © 2022 IEEE.

Tracking Changes in Mobility Before and After the First SARS-CoV-2 Vaccination Using Global Positioning System Data in England and Wales (Virus Watch): Prospective Observational Community Cohort Study.

BACKGROUND: Evidence suggests that individuals may change adherence to public health policies aimed at reducing the contact, transmission, and spread of the SARS-CoV-2 virus after they receive their first SARS-CoV-2 vaccination when they are not fully vaccinated. OBJECTIVE: We aimed to estimate changes in median daily travel distance of our cohort from their registered addresses before and after receiving a SARS-CoV-2 vaccine. METHODS: Participants were recruited into Virus Watch starting in June 2020. Weekly surveys were sent out to participants, and vaccination status was collected from January 2021 onward. Between September 2020 and February 2021, we invited 13,120 adult Virus Watch participants to contribute toward our tracker subcohort, which uses the GPS via a smartphone app to collect data on movement. We used segmented linear regression to estimate the median daily travel distance before and after the first self-reported SARS-CoV-2 vaccine dose. RESULTS: We analyzed the daily travel distance of 249 vaccinated adults. From 157 days prior to vaccination until the day before vaccination, the median daily travel distance was 9.05 (IQR 8.06-10.09) km. From the day of vaccination to 105 days after vaccination, the median daily travel distance was 10.08 (IQR 8.60-12.42) km. From 157 days prior to vaccination until the vaccination date, there was a daily median decrease in mobility of 40.09 m (95% CI -50.08 to -31.10; P<.001). After vaccination, there was a median daily increase in movement of 60.60 m (95% CI 20.90-100; P<.001). Restricting the analysis to the third national lockdown (January 4, 2021, to April 5, 2021), we found a median daily movement increase of 18.30 m (95% CI -19.20 to 55.80; P=.57) in the 30 days prior to vaccination and a median daily movement increase of 9.36 m (95% CI 38.6-149.00; P=.69) in the 30 days after vaccination. CONCLUSIONS: Our study demonstrates the feasibility of collecting high-volume geolocation data as part of research projects and the utility of these data for understanding public health issues. Our various analyses produced results that ranged from no change in movement after vaccination (during the third national lock down) to an increase in movement after vaccination (considering all periods, up to 105 days after vaccination), suggesting that, among Virus Watch participants, any changes in movement distances after vaccination are small. Our findings may be attributable to public health measures in place at the time such as movement restrictions and home working that applied to the Virus Watch cohort participants during the study period.

Geospatial, earth observations and statistical data integration in the Cortés department, Honduras

Proper territorial data management is critical for territorial planning projects, research, innovation, and the appropriate follow-up to act for the well-being of populations. A multidisciplinary team of professionals established a pilot project named Cortes Data Hub (Centro de Datos de Cortés). It presents several dashboards that show official statistics on the energy sector, mapping the region's energy demand, data on COVID-19 cases and vaccination rates by municipality or department, and a project using Google Earth that combines post-Eta and Iota observations and a social media campaign for disaster awareness and for the promotion of activities to develop tourism in the San Manuel Municipality. This pilot project shows the importance to observe and monitor various key environmental, health, and socioeconomic data. This will help improve initiatives for local development, disaster prevention and control, and the promotion of the One Health approach. The challenges to overcome are the quality and timing of data. Training more academics, government teams, and decision-makers in the use of new tools for data integration with earth observations are important for the Cortés department's development. © 2022 IEEE.

Open data on Covid-19 in the Spanish autonomous communities: reutilization in spatial epidemiology studies

The Covid-19 pandemic has highlighted the need for governments and health administrations at all levels to have an open data registry that facilitates decision-making in the planning and management of health resources and provides information to citizens on the evolution of the epidemic. The concept of “open data” includes the possibility of reutilization by third parties. Space and time are basic dimensions used to structure and interpret the data of the variables that refer to the health status of the people themselves. Hence, the main objective of this study is to evaluate whether the autonomous communities’ data files regarding Covid-19 are reusable to analyze the evolution of the disease in basic spatial and temporal analysis units at the regional and national levels. To this end, open data files containing the number of diagnosed cases of Covid-19 distributed in basic health or administrative spatial units and temporal units were selected from the portals of the Spanish autonomous communities. The presence of infection-related, demographic, and temporal variables, as well as the download format and metadata, were mainly evaluated. Whether the structure of the files was homogeneous and adequate for the application of spatial analysis techniques was also analyzed. The results reveal a lack of standardization in the collection of data in both spatial and temporal units and an absence of, or ambiguity in, the meaning of the variables owing to a lack of metadata. An inadequate structure was also found in the files of seven autonomous communities, which would require subsequent processing of the data to enable their reuse and the application of analysis and spatial modeling techniques, both when carrying out global analyses and when comparing patterns of evolution between different regions. © 2022, El Profesional de la Informacion. All rights reserved.

Canadian Jobs amid a Pandemic: Examining the Relationship between Professional Industry and Salary to Regional Key Performance Indicators

The COVID-19 pandemic has contributed to un-precedented rates of unemployment and greater uncertainty in the job market. There is a growing need for data-driven tools and analyses to better inform the public on trends within the job market. In particular, obtaining a 'snapshot' of available employment opportunities mid-pandemic promises insights to inform policy and support retraining programs. In this work, we combine data scraped from the Canadian Job Bank and Numbeo globally crowd-sourced repository to explore the relationship between job postings during a global pandemic and Key Performance Indicators (e.g. quality of life [QOL] index, cost of living) for major cities across Canada. This analysis aims to help Canadians make informed career decisions, collect a 'snapshot' of the Canadian employment opportunities amid a pandemic, and inform job seekers in identifying the correct fit between the desired lifestyle of a city and their career. We collected a new high-quality dataset of job postings from jobbank.gc.ca obtained with the use of ethical web scraping and performed exploratory data analysis on this dataset to identify job opportunity trends. When optimizing for average salary of job openings with QOL, affordability, cost of living, and traffic indices, it was found that Edmonton, AB consistently scores higher than the mean, and is therefore an attractive place to move. Furthermore, we identified optimal provinces to relocate to with respect to individual skill levels. It was determined that Ajax, Marathon, and Chapleau, ON are each attractive cities for IT professionals, construction workers, and healthcare workers respectively when maximizing average salary. Finally, we publicly release our scraped dataset as a mid-pandemic snapshot of Canadian employment opportunities and present a public web application that provides an interactive visual interface that summarizes our findings for the general public and the broader research community. © 2022 IEEE.

Sentiment-Based Spatiotemporal Prediction Framework for Pandemic Outbreaks Awareness Using Social Networks Data Classification

According to the World Health Organization, several factors have affected the accurate reporting of SARS-CoV-2 outbreak status, such as limited data collection resources, cultural and educational diversity, and inconsistent outbreak reporting from different sectors. Driven by this challenging situation, this study investigates the potential expediency of using social network data to develop reliable early information surveillance and warning system for pandemic outbreaks. As such, an enhanced framework of three inherently interlinked subsystems is proposed. The first subsystem includes data collection and integration mechanisms, data preprocessing, and hybrid sentiment analysis tools to identify tweet sentiment taxonomies and quantitatively estimate public awareness. The second subsystem comprises the feature extraction unit that identifies, selects, embeds, and balances feature vectors and the classifier fitting and training unit. This subsystem is designed to capture the most effective linguistic feature combinations with more spatial evidence by using a variety of approaches, including linear classifiers, MLPs, RNNs, and CNNs, as well as pre-trained word embedding algorithms. The last is the modeling and situational awareness evaluation subsystem, which measures temporal associations between pandemic-relevant social network activities and officially announced infection counts in the most hazardous geolocations. The proposed framework was developed and tested using a combination of static datasets and real-time scraped Twitter data. The results of these experiments showed the remarkable performance of the framework in assessing the temporal associations between public awareness and outbreak status. It also showed that the Decision Tree Classifier with Unigram+TF-IDF feature vectors outperformed other conventional models for sentiment classification and geolocation classification with an accuracy of 94.3% and 80.8, respectively. As indicated, conventional machine learning algorithms didn't achieve a precision of more than 80%, while, for instance, MLP with self-embedding layer, Word2Vec, and GloVe pre-trained word embedding resulted in very poor accuracy of 10%, 36%, and 32%, respectively. However, adding the PoS tag one-hot encoding embedding increased the validation accuracy from 36% to approximately 89%, while the best performance for the second subsystem was achieved by Bi-LSTM with RoBERTa word embedding, with an accuracy of 96%. The achieved results reveal that the proposed framework can proactively capture the potential hazards associated with the prevalence of infectious diseases as an effective early detection and info-surveillance awareness system.

Astroturfing as a strategy for manipulating public opinion on Twitter during the pandemic in Spain

This work aims to establish whether astroturfing was used during the Covid-19 pandemic to manipulate Spanish public opinion through Twitter. This study analyzes tweets published in Spanish and geolocated in the Philippines, and its first objective is to determine the existence of an organized network that directs its messages mainly towards Spain. To determine the non-existence of a random network, a preliminary collection of 1,496,596 tweets was carried out. After determining its 14 main clusters, 280 users with a medium-low profile of participation and micro- and nano-influencer traits were randomly selected and followed for 103 days, for a total of 309,947 tweets. Network science, text mining, sentiment and emotion, and bot probability analyses were performed using Gephi and R. Their network structure suggests an ultra-small-world phenomenon, which would determine the existence of a possible organized network that tries not to be easily identifiable. The data analyzed confirm a digital communication scenario in which astroturfing is used as a strategy aimed at manipulating public opinion through non-influencers (cybertroops). These users create and disseminate content with proximity and closeness to different groups of public opinion, mixing topics of general interest with disinformation or polarized content.

Data Clustering Mapping of Covid-19 Pandemic Based On Geo-Location and Machine Learning

The spread of the covid-19 virus pandemic is very fast, where was start of the virus spreading from Wuhan City, Hubei Province, China and suddenly spread out widely to almost around the world. Because of the quick spread of the Covid-19 pandemic, the disease's contagious nature, and the delay of vaccine production, the only option is to prevent people from mingling in a mob. Using data mining techniques to clustering hotspots zones for impacted Corona positive patients and narrowing the focus to only those zones can be one of the suitable solution against the spread of pandemic. Up-to-date and reliable information about hotspot zones can help the government efficiently implement the measures by focusing resources on the zones, as well as notify other residents about such hotspot zones. The most typical use of hotspot detection in public health is to identify the outbreaks of diseases. There are many Clustering algorithms used for clustering COVID-19 Pandemic, this research aims to compare between two method of clustering technique DBSCAN (Density-Based Spatial Clustering of Applications with Noise) and K-Means, and evaluate the performances of these clustering algorithms using Silhouette score values for both and elbow method for K-mean, and discuss which one is fit for purpose of clustering the hotspot, to produce a powerful hotspot map that can help the decision makers. The proposed approaches are evaluated using Data Science for COVID-19 (DS4C) dataset. The dataset was retrieved from the official repository of the Korea Centre for Disease Control and Prevention (KCDC). From data testing for 244 patient's geolocation (Long., Lat.), show that DBSCAN method separate the data to 4 main cluster noise points with eps=0.45 and minimum pts=20, and for K-Means method with k = 4, including all points, as no noise points in K-mean cluster method.

Revealing the linguistic and geographical disparities of public awareness to Covid-19 outbreak through social media

The Covid-19 has presented an unprecedented challenge to public health worldwide. However, residents in different countries showed diverse levels of Covid-19 awareness during the outbreak and suffered from uneven health impacts. This study analyzed the global Twitter data from January 1st to June 30(th), 2020, to answer two research questions. What are the linguistic and geographical disparities of public awareness in the Covid-19 outbreak period reflected on social media? Does significant association exist between the changing Covid-19 awareness and the pandemic outbreak? We established a Twitter data mining framework calculating the Ratio index to quantify and track awareness. The lag correlations between awareness and health impacts were examined at global and country levels. Results show that users presenting the highest Covid-19 awareness were mainly those tweeting in the official languages of India and Bangladesh. Asian countries showed more disparities in awareness than European countries, and awareness in Eastern Europe was higher than in central Europe. Finally, the Ratio index had high correlations with global mortality rate, global case fatality ratio, and country-level mortality rate, with 21-31, 35-42, and 13-18 leading days, respectively. This study yields timely insights into social media use in understanding human behaviors for public health research.

An Edge Computing and Ambient Data Capture System for Clinical and Home Environments.

The non-contact patient monitoring paradigm moves patient care into their homes and enables long-term patient studies. The challenge, however, is to make the system non-intrusive, privacy-preserving, and low-cost. To this end, we describe an open-source edge computing and ambient data capture system, developed using low-cost and readily available hardware. We describe five applications of our ambient data capture system. Namely: (1) Estimating occupancy and human activity phenotyping; (2) Medical equipment alarm classification; (3) Geolocation of humans in a built environment; (4) Ambient light logging; and (5) Ambient temperature and humidity logging. We obtained an accuracy of 94% for estimating occupancy from video. We stress-tested the alarm note classification in the absence and presence of speech and obtained micro averaged F1 scores of 0.98 and 0.93, respectively. The geolocation tracking provided a room-level accuracy of 98.7%. The root mean square error in the temperature sensor validation task was 0.3°C and for the humidity sensor, it was 1% Relative Humidity. The low-cost edge computing system presented here demonstrated the ability to capture and analyze a wide range of activities in a privacy-preserving manner in clinical and home environments and is able to provide key insights into the healthcare practices and patient behaviors.

Social Distancing and Voice Alerting Using Unmanned Aerial Vehicles

A pandemic like COVID-19 has conveyed the necessity of maintaining social distancing between two or more human beings. However, it is not possible for police or government officials to be omnipresent and regulate gatherings all around. This paper presents a model for maintaining social distancing norms using Unmanned Aerial Vehicles (UAV) which helps in aerial surveillance and detecting humans using Hierarchical Extreme Learning Machine(HELM), estimating their geolocations, and calculating the distance between two immediate beings and alerting them in case they are in close proximity with another body using on-board systems and algorithms. The human being is alerted through a prerecorded audio clip played through a speaker present on the UAV to maintain necessary distance. Furthermore, the use-case is expanded for surveillance and crowd control measures by alerting the local authorities in case of a mass gathering in a region. This approach minimizes the deployment of personnel for ensuring and monitoring social distancing and helps regulate crowd gatherings using cyber-physical systems. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

Designing An Attendance System Model for Work from Home (WFH) Employees Based on User-Centered

Attendance system has evolved along with the industrial revolution that now has reached a new era. Furthermore, nowadays with the struck of COVID-19, the government issued a prohibition policy towards companies to urge their employees to work from home (WFH). Several issues have come across the Human Resources Development (HRD) manager regarding this policy. Employees' taking vacation when they are obliged to work from home and employees' faking their attendance are two of many problems regarding this policy. Hence, this study aims to design a relevant attendance system model that will overcome these problems with the integration of face recognition and geolocation through mobile platform. The study built the proposed attendance system with the approach of User-Centered Design (UCD) methodology. The findings within the study shows that above 80% of participants are satisfied with the proposed model and are ready to implement the designed system in their organizations respectively. © 2021 IEEE.

COVID-19 Contact Tracing Using Geolocation

COVID-19 is an infectious disease caused by the newly discovered coronavirus. With the number of detected cases increasing exponentially each day, it is very challenging to track the movements of an infected person for the duration of the incubation period of the virus. As there is no active vaccination that has been developed yet, it has become a huge concern globally to mitigate the effects of this virus. Countries across the world have been looking for ways to prevent the spread of this disease. There are various precautionary measures implemented worldwide, but this might not be very effective in the future for containing the transmission of the virus. This necessitates the development of a technique which can help track the whereabouts of the infected person and trace the spread of the virus. The aim of this paper is to discuss our progressive Web application (PWA) which compares and matches the user’s data with the data of a patient who has tested positive for COVID-19. This PWA uses geolocation to find the real-world geographic location of a person without Bluetooth and GPS turned on at all times. It alerts a user if they have come in contact with a COVID-positive patient in any particular place at any specific instance of time to take the necessary precautions. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

Predicting Geolocation of Tweets: Using Combination of CNN and BiLSTM.

Twitter is one of the most popular micro-blogging and social networking platforms where users post their opinions, preferences, activities, thoughts, views, etc., in form of tweets within the limit of 280 characters. In order to study and analyse the social behavior and activities of a user across a region, it becomes necessary to identify the location of the tweet. This paper aims to predict geolocation of real-time tweets at the city level collected for a period of 30 days by using a combination of convolutional neural network and a bidirectional long short-term memory by extracting features within the tweets and features associated with the tweets. We have also compared our results with previous baseline models and the findings of our experiment show a significant improvement over baselines methods achieving an accuracy of 92.6 with a median error of 22.4 km at city level prediction.

A snapshot of a pandemic: The interplay between social isolation and COVID-19 dynamics in Brazil.

In response to the coronavirus pandemic, governments implemented social distancing, attempting to block the virus spread within territories. While it is well accepted that social isolation plays a role in epidemic control, the precise connections between mobility data indicators and epidemic dynamics are still a challenge. In this work, we investigate the dependency between a social isolation index and epidemiological metrics for several Brazilian cities. Classic statistical methods are employed to support the findings. As a first, initially surprising, result, we illustrate how there seems to be no apparent functional relationship between social isolation data and later effects on disease incidence. However, further investigations identified two regimes of successful employment of social isolation: as a preventive measure or as a remedy, albeit remedy measures require greater social isolation and bring higher burden to health systems. Additionally, we exhibit cases of successful strategies involving lockdowns and an indicator-based mobility restriction plan.

Word embeddings and deep learning for location prediction: tracking Coronavirus from British and American tweets.

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.