Use of Twitter social media activity as a proxy for human mobility to predict the spatiotemporal spread of COVID-19 at global scale

A conceptional model integrating geographic information systems (GIS) and social media data for disease exposure assessment

Although previous studies have acknowledged the potential of geographic information systems (GIS) and social media data (SMD) in assessment of exposure to various environmental risks, none has presented a simple, effective and user-friendly tool. This study introduces a conceptual model that integrates individual mobility patterns extracted from social media, with the geographic footprints of infectious diseases and other environmental agents utilizing GIS. The efficacy of the model was independently evaluated for selected case studies involving lead in the ground; particulate matter in the air; and an infectious, viral disease (COVID- 19). A graphical user interface (GUI) was developed as the final output of this study. Overall, the evaluation of the model demonstrated feasibility in successfully extracting individual mobility patterns, identifying potential exposure sites and quantifying the frequency and magnitude of exposure. Importantly, the novelty of the developed model lies not merely in its efficiency in integrating GIS and SMD for exposure assessment, but also in considering the practical requirements of health practitioners. Although the conceptual model, developed together with its associated GUI, presents a promising and practical approach to assessment of the exposure to environmental risks discussed here, its applicability, versatility and efficacy extends beyond the case studies presented in this study.

Methods and Annotated Data Sets Used to Predict the Gender and Age of Twitter Users: Scoping Review

BACKGROUND

Patient health data collected from a variety of nontraditional resources, commonly referred to as real-world data, can be a key information source for health and social science research. Social media platforms, such as Twitter (Twitter, Inc), offer vast amounts of real-world data. An important aspect of incorporating social media data in scientific research is identifying the demographic characteristics of the users who posted those data. Age and gender are considered key demographics for assessing the representativeness of the sample and enable researchers to study subgroups and disparities effectively. However, deciphering the age and gender of social media users poses challenges.

OBJECTIVE

This scoping review aims to summarize the existing literature on the prediction of the age and gender of Twitter users and provide an overview of the methods used.

METHODS

We searched 15 electronic databases and carried out reference checking to identify relevant studies that met our inclusion criteria: studies that predicted the age or gender of Twitter users using computational methods. The screening process was performed independently by 2 researchers to ensure the accuracy and reliability of the included studies.

RESULTS

Of the initial 684 studies retrieved, 74 (10.8%) studies met our inclusion criteria. Among these 74 studies, 42 (57%) focused on predicting gender, 8 (11%) focused on predicting age, and 24 (32%) predicted a combination of both age and gender. Gender prediction was predominantly approached as a binary classification task, with the reported performance of the methods ranging from 0.58 to 0.96 F1-score or 0.51 to 0.97 accuracy. Age prediction approaches varied in terms of classification groups, with a higher range of reported performance, ranging from 0.31 to 0.94 F1-score or 0.43 to 0.86 accuracy. The heterogeneous nature of the studies and the reporting of dissimilar performance metrics made it challenging to quantitatively synthesize results and draw definitive conclusions.

CONCLUSIONS

Our review found that although automated methods for predicting the age and gender of Twitter users have evolved to incorporate techniques such as deep neural networks, a significant proportion of the attempts rely on traditional machine learning methods, suggesting that there is potential to improve the performance of these tasks by using more advanced methods. Gender prediction has generally achieved a higher reported performance than age prediction. However, the lack of standardized reporting of performance metrics or standard annotated corpora to evaluate the methods used hinders any meaningful comparison of the approaches. Potential biases stemming from the collection and labeling of data used in the studies was identified as a problem, emphasizing the need for careful consideration and mitigation of biases in future studies. This scoping review provides valuable insights into the methods used for predicting the age and gender of Twitter users, along with the challenges and considerations associated with these methods.

Revealing geographic transmission pattern of COVID-19 using neighborhood-level simulation with human mobility data and SEIR model: A case study of South Carolina

Direct human physical contact accelerates COVID-19 transmission. Smartphone mobility data has emerged as a valuable data source for revealing fine-grained human mobility, which can be used to estimate the intensity of physical contact surrounding different locations. Our study applied smartphone mobility data to simulate the second wave spreading of COVID-19 in January 2021 in three major metropolitan statistical areas (Columbia, Greenville, and Charleston) in South Carolina, United States. Based on the simulation, the number of historical county-level COVID-19 cases was allocated to neighborhoods (Census block groups) and points of interest (POIs), and the transmission rate of each allocated place was estimated. The result reveals that the COVID-19 infections during the study period mainly occurred in neighborhoods (86%), and the number is approximately proportional to the neighborhood's population. Restaurants and elementary and secondary schools contributed more COVID-19 infections than other POI categories. The simulation results for the coastal tourism Charleston area show high transmission rates in POIs related to travel and leisure activities. The results suggest that neighborhood-level infectious controlling measures are critical in reducing COVID-19 infections. We also found that households of lower socioeconomic status may be an umbrella against infection due to fewer visits to places such as malls and restaurants associated with their low financial status. Control measures should be tailored to different geographic locations since transmission rates and infection counts of POI categories vary among metropolitan areas.

Social media mining under the COVID-19 context: Progress, challenges, and opportunities

Social media platforms allow users worldwide to create and share information, forging vast sensing networks that allow information on certain topics to be collected, stored, mined, and analyzed in a rapid manner. During the COVID-19 pandemic, extensive social media mining efforts have been undertaken to tackle COVID-19 challenges from various perspectives. This review summarizes the progress of social media data mining studies in the COVID-19 contexts and categorizes them into six major domains, including early warning and detection, human mobility monitoring, communication and information conveying, public attitudes and emotions, infodemic and misinformation, and hatred and violence. We further document essential features of publicly available COVID-19 related social media data archives that will benefit research communities in conducting replicable and reproducible studies. In addition, we discuss seven challenges in social media analytics associated with their potential impacts on derived COVID-19 findings, followed by our visions for the possible paths forward in regard to social media-based COVID-19 investigations. This review serves as a valuable reference that recaps social media mining efforts in COVID-19 related studies and provides future directions along which the information harnessed from social media can be used to address public health emergencies.

Revealing geographic transmission pattern of COVID-19 using neighborhood-level simulation with human mobility data and SEIR model: A Case Study of South Carolina

Direct human physical contact accelerates COVID-19 transmission. Smartphone mobility data has been an emerging data source to reveal fine-grained human mobility, which can be used to estimate the intensity of physical contact surrounding different locations. Our study applied smartphone mobility data to simulate the second wave spreading of COVID-19 in January 2021 in three major metropolitan statistical areas (Columbia, Greenville, and Charleston) in South Carolina, United States. Based on the simulation, the number of historical county-level COVID-19 cases was allocated to neighborhoods (Census blockgroups) and points of interest (POIs), and the transmission rate of each allocated place was estimated. The result reveals that the COVID-19 infections during the study period mainly occurred in neighborhoods (86%), and the number is approximately proportional to the neighborhood’s population. Restaurants and elementary and secondary schools contributed more COVID-19 infections than other POI categories. The simulation results for the coastal tourism Charleston area show high transmission rates in POIs related to travel and leisure activities. The results suggest that the neighborhood-level infectious controlling measures are critical in reducing COVID-19 infections. We also found that the households of lower socioeconomic status may be an umbrella against infection due to fewer visits to places such as malls and restaurants associated with their low financial status. Control measures should be tailored to different geographic locations since transmission rates and infection counts of POI categories vary among metropolitan areas.

Identifying the Socioeconomic, Demographic, and Political Determinants of Social Mobility and Their Effects on COVID-19 Cases and Deaths: Evidence From US Counties

Background

The spread of COVID-19 at the local level is significantly impacted by population mobility. The U.S. has had extremely high per capita COVID-19 case and death rates. Efficient nonpharmaceutical interventions to control the spread of COVID-19 depend on our understanding of the determinants of public mobility.

Objective

This study used publicly available Google data and machine learning to investigate population mobility across a sample of US counties. Statistical analysis was used to examine the socioeconomic, demographic, and political determinants of mobility and the corresponding patterns of per capita COVID-19 case and death rates.

Methods

Daily Google population mobility data for 1085 US counties from March 1 to December 31, 2020, were clustered based on differences in mobility patterns using K-means clustering methods. Social mobility indicators (retail, grocery and pharmacy, workplace, and residence) were compared across clusters. Statistical differences in socioeconomic, demographic, and political variables between clusters were explored to identify determinants of mobility. Clusters were matched with daily per capita COVID-19 cases and deaths.

Results

Our results grouped US counties into 4 Google mobility clusters. Clusters with more population mobility had a higher percentage of the population aged 65 years and over, a greater population share of Whites with less than high school and college education, a larger percentage of the population with less than a college education, a lower percentage of the population using public transit to work, and a smaller share of voters who voted for Clinton during the 2016 presidential election. Furthermore, clusters with greater population mobility experienced a sharp increase in per capita COVID-19 case and death rates from November to December 2020.

Conclusions

Republican-leaning counties that are characterized by certain demographic characteristics had higher increases in social mobility and ultimately experienced a more significant incidence of COVID-19 during the latter part of 2020.

Public Attitudes During the Second Lockdown: Sentiment and Topic Analyses Using Tweets From Ontario, Canada

Objective: This study aimed to explore topics and sentiments using tweets from Ontario, Canada, during the second wave of the COVID-19 pandemic.

Methods: Tweets were collected from December 5, 2020, to March 6, 2021, excluding non-individual accounts. Dates of vaccine-related events and policy changes were collected from public health units in Ontario. The daily number of COVID-19 cases was retrieved from the Ontario provincial government’s public health database. Latent Dirichlet Allocation was used for unsupervised topic modelling. VADER was used to calculate daily and average sentiment compound scores for topics identified.

Results: Vaccine, pandemic, business, lockdown, mask, and Ontario were six topics identified from the unsupervised topic modelling. The average sentiment compound score for each topic appeared to be slightly positive, yet the daily sentiment compound scores varied greatly between positive and negative emotions for each topic.

Conclusion: Our study results have shown a slightly positive sentiment on average during the second wave of the COVID-19 pandemic in Ontario, along with six topics. Our research has also demonstrated a social listening approach to identify what the public sentiments and opinions are in a timely manner.

An analysis of twitter as a relevant human mobility proxy: A comparative approach in spain during the COVID-19 pandemic

During the last years, the analysis of spatio-temporal data extracted from Online Social Networks (OSNs) has become a prominent course of action within the human-mobility mining discipline. Due to the noisy and sparse nature of these data, an important effort has been done on validating these platforms as suitable mobility proxies. However, such a validation has been usually based on the computation of certain features from the raw spatio-temporal trajectories extracted from OSN documents. Hence, there is a scarcity of validation studies that evaluate whether geo-tagged OSN data are able to measure the evolution of the mobility in a region at multiple spatial scales. For that reason, this work proposes a comprehensive comparison of a nation-scale Twitter (TWT) dataset and an official mobility survey from the Spanish National Institute of Statistics. The target time period covers a three-month interval during which Spain was heavily affected by the COVID-19 pandemic. Both feeds have been compared in this context by considering different mobility-related features and spatial scales. The results show that TWT could capture only a limited number features of the latent mobility behaviour of Spain during the study period.

Understanding internal migration in the UK before and during the COVID-19 pandemic using twitter data

The COVID-19 pandemic has greatly affected internal migration patterns and may last beyond the pandemic. It raises the need to monitor the migration in an economical, effective and timely way. Benefitting from the advancement of geolocation data collection techniques, we used near real-time and fine-grained Twitter data to monitor migration patterns during the COVID-19 pandemic, dated from January 2019 to December 2021. Based on geocoding and estimating home locations, we proposed five indices depicting migration patterns, which are demonstrated by applying an empirical study at national and local authority scales to the UK. Our findings point to complex social processes unfolding differently over space and time. In particular, the pandemic and lockdown policies significantly reduced the rate of migration. Furthermore, we found a trend of people moving out of large cities to the nearby rural areas, and also conjunctive cities if there is one, before and during the peak of the pandemic. The trend of moving to rural areas became more significant in 2020 and most people who moved out had not returned by the end of 2021, although large cities recovered more quickly than other regions. Our results of monthly migration matrixes are validated to be consistent with official migration flow data released by the Office for National Statistics, but have finer temporal granularity and can be updated more frequently. This study demonstrates that Twitter data is highly valuable for migration trend analysis despite the biases in population representation.

Emerging geo-data sources to reveal human mobility dynamics during COVID-19 pandemic: opportunities and challenges

Effectively monitoring the dynamics of human mobility is of great importance in urban management, especially during the COVID-19 pandemic. Traditionally, the human mobility data is collected by roadside sensors, which have limited spatial coverage and are insufficient in large-scale studies. With the maturing of mobile sensing and Internet of Things (IoT) technologies, various crowdsourced data sources are emerging, paving the way for monitoring and characterizing human mobility during the pandemic. This paper presents the authors’ opinions on three types of emerging mobility data sources, including mobile device data, social media data, and connected vehicle data. We first introduce each data source’s main features and summarize their current applications within the context of tracking mobility dynamics during the COVID-19 pandemic. Then, we discuss the challenges associated with using these data sources. Based on the authors’ research experience, we argue that data uncertainty, big data processing problems, data privacy, and theory-guided data analytics are the most common challenges in using these emerging mobility data sources. Last, we share experiences and opinions on potential solutions to address these challenges and possible research directions associated with acquiring, discovering, managing, and analyzing big mobility data.

Introducing Twitter Daily Estimates of Residents and Non-Residents at the County Level

The study of migrations and mobility has historically been severely limited by the absence of reliable data or the temporal sparsity of available data. Using geospatial digital trace data, the study of population movements can be much more precisely and dynamically measured. Our research seeks to develop a near real-time (one-day lag) Twitter census that gives a more temporally granular picture of local and non-local population at the county level. Internal validation reveals over 80% accuracy when compared with users’ self-reported home location. External validation results suggest these stocks correlate with available statistics of residents/non-residents at the county level and can accurately reflect regular (seasonal tourism) and non-regular events such as the Great American Solar Eclipse of 2017. The findings demonstrate that Twitter holds the potential to introduce the dynamic component often lacking in population estimates. This study could potentially benefit various fields such as demography, tourism, emergency management, and public health and create new opportunities for large-scale mobility analyses.

Spatiotemporal Patterns of Human Mobility and Its Association with Land Use Types during COVID-19 in New York City

The novel coronavirus disease (COVID-19) pandemic has impacted every facet of society. One of the non-pharmacological measures to contain the COVID-19 infection is social distancing. Federal, state, and local governments have placed multiple executive orders for human mobility reduction to slow down the spread of COVID-19. This paper uses geotagged tweets data to reveal the spatiotemporal human mobility patterns during this COVID-19 pandemic in New York City. With New York City open data, human mobility pattern changes were detected by different categories of land use, including residential, parks, transportation facilities, and workplaces. This study further compares human mobility patterns by land use types based on an open social media platform (Twitter) and the human mobility patterns revealed by Google Community Mobility Report cell phone location, indicating that in some applications, open-access social media data can generate similar results to private data. The results of this study can be further used for human mobility analysis and the battle against COVID-19.

Spatial-Temporal Relationship Between Population Mobility and COVID-19 Outbreaks in South Carolina: Time Series Forecasting Analysis

BACKGROUND

Population mobility is closely associated with COVID-19 transmission, and it could be used as a proximal indicator to predict future outbreaks, which could inform proactive nonpharmaceutical interventions for disease control. South Carolina is one of the US states that reopened early, following which it experienced a sharp increase in COVID-19 cases.

OBJECTIVE

The aims of this study are to examine the spatial-temporal relationship between population mobility and COVID-19 outbreaks and use population mobility data to predict daily new cases at both the state and county level in South Carolina.

METHODS

This longitudinal study used disease surveillance data and Twitter-based population mobility data from March 6 to November 11, 2020, in South Carolina and its five counties with the largest number of cumulative confirmed COVID-19 cases. Population mobility was assessed based on the number of Twitter users with a travel distance greater than 0.5 miles. A Poisson count time series model was employed for COVID-19 forecasting.

RESULTS

Population mobility was positively associated with state-level daily COVID-19 incidence as well as incidence in the top five counties (ie, Charleston, Greenville, Horry, Spartanburg, and Richland). At the state level, the final model with a time window within the last 7 days had the smallest prediction error, and the prediction accuracy was as high as 98.7%, 90.9%, and 81.6% for the next 3, 7, and 14 days, respectively. Among Charleston, Greenville, Horry, Spartanburg, and Richland counties, the best predictive models were established based on their observations in the last 9, 14, 28, 20, and 9 days, respectively. The 14-day prediction accuracy ranged from 60.3%-74.5%.

CONCLUSIONS

Using Twitter-based population mobility data could provide acceptable predictions of COVID-19 daily new cases at both the state and county level in South Carolina. Population mobility measured via social media data could inform proactive measures and resource relocations to curb disease outbreaks and their negative influences.

Spatial-temporal relationship between population mobility and COVID-19 outbreaks in South Carolina: A time series forecasting analysis

BACKGROUND

Population mobility is closely associated with coronavirus 2019 (COVID-19) transmission, and it could be used as a proximal indicator to predict future outbreaks, which could inform proactive non-pharmaceutical interventions for disease control. South Carolina (SC) is one of the states which reopened early and then suffered from a sharp increase of COVID-19.

OBJECTIVE

To examine the spatial-temporal relationship between population mobility and COVID-19 outbreaks and use population mobility to predict daily new cases at both state- and county- levels in SC.

METHODS

This longitudinal study used disease surveillance data and Twitter-based population mobility data from March 6 to November 11, 2020 in SC and its top five counties with the largest number of cumulative confirmed cases. Daily new case was calculated by subtracting the cumulative confirmed cases of previous day from the total cases. Population mobility was assessed using the number of users with travel distance larger than 0.5 mile which was calculated based on their geotagged twitters. Poisson count time series model was employed to carry out the research goals.

RESULTS

Population mobility was positively associated with state-level daily COVID-19 incidence and those of the top five counties (i.e., Charleston, Greenville, Horry, Spartanburg, Richland). At the state-level, final model with time window within the last 7-day had the smallest prediction error, and the prediction accuracy was as high as 98.7%, 90.9%, and 81.6% for the next 3-, 7-, 14- days, respectively. Among Charleston, Greenville, Horry, Spartanburg, and Richland counties, the best predictive models were established based on their observations in the last 9-, 14-, 28-, 20-, and 9- days, respectively. The 14-day prediction accuracy ranged from 60.3% to 74.5%.

CONCLUSIONS

Population mobility was positively associated with COVID-19 incidences at both state- and county- levels in SC. Using Twitter-based mobility data could provide acceptable prediction for COVID-19 daily new cases. Population mobility measured via social media platform could inform proactive measures and resource relocations to curb disease outbreaks and their negative influences.

Spatial Temporal Analysis of Traffic Patterns during the COVID-19 Epidemic by Vehicle Detection Using Planet Remote-Sensing Satellite Images

The spread of the COVID-19 since the end of 2019 has reached an epidemic level and has quickly become a global public health crisis. During this period, the responses for COVID-19 were highly diverse and decentralized across countries and regions. Understanding the dynamics of human mobility change at high spatial temporal resolution is critical for assessing the impacts of non-pharmaceutical interventions (such as stay-at-home orders, regional lockdowns and travel restrictions) during the pandemic. However, this requires collecting traffic data at scale, which is time-consuming, cost-prohibitive and often not available (e.g., in underdeveloped countries). Therefore, spatiotemporal analysis through processing periodical remote-sensing images is very beneficial to enable efficient monitoring at the global scale. In this paper, we present a novel study that utilizes high temporal Planet multispectral images (from November 2019 to September 2020, on average 7.1 days of frequency) to detect traffic density in multiple cities through a proposed morphology-based vehicle detection method and evaluate how the traffic data collected in such a manner reflect mobility pattern changes in response to COVID-19. Our experiments at city-scale detection, demonstrate that our proposed vehicle detection method over this 3 m resolution data is able to achieve a detection level at an accuracy of 68.26% in most of the images, and the observations’ trends coincide with existing public data of where available (lockdown duration, traffic volume, etc.), further suggesting that such high temporal Planet data with global coverage (although not with the best resolution), with well-devised detection algorithms, can sufficiently provide traffic details for trend analysis to better facilitate informed decision making for extreme events at the global level.

First year with COVID-19: Assessment and prospects

The vision of health for all by Dr. Halfdan Mahler, Director General of the World Health Organization (WHO) 1973 to 1988, guided public health approaches towards improving life for all those mired in poverty and disease. Research on the Neglected Tropical Diseases (NTDs) of the world's poor was advancing strongly when the coronavirus disease 2019 (COVID-19) struck. Although work on the NTDs did not grind to a halt, the situation is reminiscent of the author Stefan Zweig's passionate account of culture destruction in his book The World of Yesterday from 1941, which gives an insight as to how the war ended traditional life. His thoughts parallel the present situation; however, this time societies are not torn apart by war but instead isolated by a pandemic. It comes upon today's scientists to move fast to make COVID-19 less devastating than the Spanish flu of 1918-1920 that killed more than 3% of the world population...

Bots as Active News Promoters: A Digital Analysis of COVID-19 Tweets

In this study, we examined the activities of automated social media accounts or bots that tweet or retweet referencing #COVID-19 and #COVID19. From a total sample of over 50 million tweets, we used a mixed method to extract more than 185,000 messages posted by 127 bots. Our findings show that the majority of these bots tweet, retweet and mention mainstream media outlets, promote health protection and telemedicine, and disseminate breaking news on the number of casualties and deaths caused by COVID-19. We argue that some of these bots are motivated by financial incentives, while other bots actively support the survivalist movement by emphasizing the need to prepare for the pandemic and learn survival skills. We only found a few bots that showed some suspicious activity probably due to the fact that our dataset was limited to two hashtags often used by official health bodies and academic communities.

Geolocated Twitter social media data to describe the geographic spread of SARS-CoV-2

Openly available, geotagged Twitter data from 2013 to 2015 was used to estimate the 2019–2020 human mobility patterns in and outside of China to predict the spatiotemporal spread of severe acute respiratory syndrome coronavirus 2. Countries with the highest number of visiting Twitter users outside of China were the USA, Japan, UK, Germany and Turkey. A high correlation was observed when comparing country-level Twitter user visits and reported cases.