Geo-tagged Tweets Research Articles

Correlation of Road Network Structure and Urban Mobility Intensity: An Exploratory Study Using Geo-Tagged Tweets

Urban planners have been long interested in understanding how urban structure and activities are mutually influenced. Human mobility and economic activities naturally drive the formation of road network structure and the accessibility of the latter shapes the patterns of movement flow across urban space. In this paper, we perform an exploratory study on the relationship between the street network structure and the intensity of human movement in urban areas. We focus on two cities and we utilize a dataset of geo-tagged tweets that can form a proxy to urban mobility and the corresponding street networks as obtained from OpenStreetMap. We apply three network centrality measures, including closeness, betweenness and straightness centrality, calculated at a global or local scale, as well as under mixed or individual transportation mode (e.g., driving, biking and walking) with its directional accessibility, to uncover the structural properties of urban street networks. We further design an urban area transition network and apply PageRank to capture the intensity of human mobility. Our correlation analysis indicates different centrality metrics have different levels of correlation with the intensity of human movement. The closeness centrality consistently shows the highest correlation (with a coefficient around 0.6) with human movement intensity when calculated at a global scale, while straightness centrality often shows no correlation at the global scale or weaker correlation ρ≈0.4 at the local scale. The correlation levels further depend on the type of directional accessibility and of various types of transportation modes. Hence, the directionality and transportation mode, largely ignored in the analysis of road networks, are crucial. Furthermore, the strength of the correlation varies in the two cities examined, indicating potential differences in urban spatial structure and human mobility patterns.

Different Ways Ambient and Immobile Population Distributions Influence Urban Crime Patterns

The article aims to propose a new way of estimating the ambient and immobile urban population using geotagged tweets and age structure, and to test how they are related to urban crime patterns. Using geotagged tweets and age structure data in 37 neighborhoods of Szczecin, Poland, we analyzed the following crime types that occurred during 2015–2017: burglary in commercial buildings, drug crime, fight and battery, property damage, and theft. Using negative binomial regression models, we found a positive correlation between the size of the ambient population and all investigated crime types. Additionally, neighborhoods with more immobile populations (younger than 16 or older than 65) tend to experience more commercial burglaries, but not other crime types. This may be related to the urban structure of Szczecin, Poland. Neighborhoods with higher rates of poverty and unemployment tend to experience more commercial burglaries, drug problems, property damage, and thefts. Additionally, the count of liquor stores is positively related to drug crime, fight-battery, and theft. This article suggests that the age structure of the population has an influence on the distribution of crime, thus it is necessary to tailor crime prevention strategies for different areas of the city.

Investigating social media spatiotemporal transferability for transport

Social Media have increasingly provided data about the movement of people in cities making them useful in understanding the daily life of people in different geographies. Particularly useful for travel analysis is when Social Media users allow (voluntarily or not) tracing their movement using geotagged information of their communication with these online platforms. In this paper we use geotagged tweets from 10 cities in the European Union and United States of America to extract spatiotemporal patterns, study differences and commonalities among these cities, and explore the nature of user location recurrence. The analysis here shows the distinction between residents and tourists is fundamental for the development of city-wide models. Identification of repeated rates of location (recurrence) can be used to define activity spaces. Differences and similarities across different geographies emerge from this analysis in terms of local distributions but also in terms of the worldwide reach among the cities explored here. The comparison of the temporal signature between geotagged and non-geotagged tweets also shows similar temporal distributions that capture in essence city rhythms of tweets and activity spaces.

Twitter conversations predict the daily confirmed COVID-19 cases

As of writing this paper, COVID-19 (Coronavirus disease 2019) has spread to more than 220 countries and territories. Following the outbreak, the pandemic’s seriousness has made people more active on social media, especially on the microblogging platforms such as Twitter and Weibo. The pandemic-specific discourse has remained on-trend on these platforms for months now. Previous studies have confirmed the contributions of such socially generated conversations towards situational awareness of crisis events. The early forecasts of cases are essential to authorities to estimate the requirements of resources needed to cope with the outgrowths of the virus. Therefore, this study attempts to incorporate the public discourse in the design of forecasting models particularly targeted for the steep-hill region of an ongoing wave. We propose a sentiment-involved topic-based latent variables search methodology for designing forecasting models from publicly available Twitter conversations. As a use case, we implement the proposed methodology on Australian COVID-19 daily cases and Twitter conversations generated within the country. Experimental results: (i) show the presence of latent social media variables that Granger-cause the daily COVID-19 confirmed cases, and (ii) confirm that those variables offer additional prediction capability to forecasting models. Further, the results show that the inclusion of social media variables introduces 48.83%–51.38% improvements on RMSE over the baseline models. We also release the large-scale COVID-19 specific geotagged global tweets dataset, MegaGeoCOV, to the public anticipating that the geotagged data of this scale would aid in understanding the conversational dynamics of the pandemic through other spatial and temporal contexts.

A multi-level analytic framework for disaster situational awareness using Twitter data

During a natural disaster, mining messages from social media platforms can facilitate local agencies, rescue teams, humanitarian aid organizations, etc., to track the situational awareness of the public. However, for different stakeholders, the concerns about people’s situational awareness in a natural disaster event are different. Therefore, I developed a Twitter-based analytic framework to take perception-level situational awareness, humanitarian-level situational awareness, and action-level situational awareness into consideration. Specifically, perception-level situational awareness mainly reflects people’s perception of the ongoing natural disaster event (i.e., if people are discussing the disaster event). Decision-makers can rapidly have a big picture of severely impacted regions. Humanitarian-level situational awareness represents tweets that are associated with the humanitarian categories based on the definition from the United Nations Office for the Coordination of Humanitarian Affairs. The detection of humanitarian-level situational awareness can help response teams understand the specific situations and needs of local communities. In terms of the action-level situational awareness, I extracted noun-verb pairs in each tweet to explicitly represent the specific event described in a given tweet, so that the response teams can quickly act on the situation case by case. Moreover, to shed light on disaster resilience and social vulnerability, I further examined the demographic characteristics of three levels of situational awareness. I empirically demonstrated the analytic framework using geo-tagged tweets during 2018 Hurricane Michael.

Three dimensions of COVID-19 risk perceptions and their socioeconomic correlates in the United States: A social media analysis.

Social media analysis provides an alternate approach to monitoring and understanding risk perceptions regarding COVID‐19 over time. Our current understandings of risk perceptions regarding COVID‐19 do not disentangle the three dimensions of risk perceptions (perceived susceptibility, perceived severity, and negative emotion) as the pandemic has evolved. Data are also limited regarding the impact of social determinants of health (SDOH) on COVID‐19‐related risk perceptions over time. To address these knowledge gaps, we extracted tweets regarding COVID‐19‐related risk perceptions and developed indicators for the three dimensions of risk perceptions based on over 502 million geotagged tweets posted by over 4.9 million Twitter users from January 2020 to December 2021 in the United States. We examined correlations between risk perception indicator scores and county‐level SDOH. The three dimensions of risk perceptions demonstrate different trajectories. Perceived severity maintained a high level throughout the study period. Perceived susceptibility and negative emotion peaked on March 11, 2020 (COVID‐19 declared global pandemic by WHO) and then declined and remained stable at lower levels until increasing once again with the Omicron period. Relative frequency of tweet posts on risk perceptions did not closely follow epidemic trends of COVID‐19 (cases, deaths). Users from socioeconomically vulnerable counties showed lower attention to perceived severity and susceptibility of COVID‐19 than those from wealthier counties. Examining trends in tweets regarding the multiple dimensions of risk perceptions throughout the COVID‐19 pandemic can help policymakers frame in‐time, tailored, and appropriate responses to prevent viral spread and encourage preventive behavior uptake in the United States.

Are Crime and Collective Emotion Interrelated? A “Broken Emotion” Conjecture from Community Twitter Posts

A neighborhood’s social cohesion, referring to the emotional and social connection of people within it, tends to have an influential impact on its crime level. Traditional approaches to measuring social cohesion and collective efficacy are mostly interviews and surveys, which are usually costly in time, money, and other resources. Big social media data provides us with a new and cost-effective source of such information. We believe the combination of spatial and contextual information of geotagged Twitter posts (tweets) can gauge the residents’ collective emotions in a neighborhood. The positivity and negativity of these collective emotions may be used to approximate the collective efficacy of the community. Inspired by the broken window theory, we propose a broken emotion conjecture to explain the relationship between collective emotion and crime. To test this conjecture, we collected data on four types of crime (assaults, burglaries, robberies, and thefts) and all public geotagged tweets ( N = 778,901) in Cincinnati, Ohio, USA in 2013. We extracted innovative variables from tweets’ spatial and contextual information to explain community crime and enlighten new criminology theory. Results of negative binomial models show: (1) with necessary socio-economic and land-use factors controlled, the more negative the collective emotion of a neighborhood, the more the crime (except for theft); (2) however, the positivity of the collective emotion of a neighborhood does not have any statistically significant influence on crime. These correspond well with signal detection theory in psychology. The proposed broken emotion conjecture is supported with data from Cincinnati and its general applicability should be tested in other regions.

Diet during the COVID-19 pandemic: An analysis of Twitter data

SummaryIn this study, we measured the association between county characteristics and changes in healthy-food, fast-food, and alcohol tweets during the COVID-19 pandemic in the United States. Our analytic dataset consisted of 1,282,316 geotagged tweets that referenced food consumption posted before (63.2%) and during (36.8%) the pandemic and included all US states. We found the share of healthy-food tweets increased by 20.5% during the pandemic compared with pre-pandemic, while fast-food and alcohol tweets decreased by 9.4% and 11.4%, respectively. We also observed that time spent at home and more grocery stores per capita were associated with increased odds of healthy-food tweets and decreased odds of fast-food tweets. More liquor stores per capita was associated with increased odds of alcohol tweets. Our results highlight the potential impact of the pandemic on nutrition and alcohol consumption and the association between the built environment and health behaviors.

The Associations Between Racially/Ethnically Stratified COVID-19 Tweets and COVID-19 Cases and Deaths: Cross-sectional Study.

BackgroundThe COVID-19 pandemic exacerbated existing racial/ethnic health disparities in the United States. Monitoring nationwide Twitter conversations about COVID-19 and race/ethnicity could shed light on the impact of the pandemic on racial/ethnic minorities and help address health disparities.ObjectiveThis paper aims to examine the association between COVID-19 tweet volume and COVID-19 cases and deaths, stratified by race/ethnicity, in the early onset of the pandemic.MethodsThis cross-sectional study used geotagged COVID-19 tweets from within the United States posted in April 2020 on Twitter to examine the association between tweet volume, COVID-19 surveillance data (total cases and deaths in April), and population size. The studied time frame was limited to April 2020 because April was the earliest month when COVID-19 surveillance data on racial/ethnic groups were collected. Racially/ethnically stratified tweets were extracted using racial/ethnic group–related keywords (Asian, Black, Latino, and White) from COVID-19 tweets. Racially/ethnically stratified tweets, COVID-19 cases, and COVID-19 deaths were mapped to reveal their spatial distribution patterns. An ordinary least squares (OLS) regression model was applied to each stratified dataset.ResultsThe racially/ethnically stratified tweet volume was associated with surveillance data. Specifically, an increase of 1 Asian tweet was correlated with 288 Asian cases (P<.001) and 93.4 Asian deaths (P<.001); an increase of 1 Black tweet was linked to 47.6 Black deaths (P<.001); an increase of 1 Latino tweet was linked to 719 Latino deaths (P<.001); and an increase of 1 White tweet was linked to 60.2 White deaths (P<.001).ConclusionsUsing racially/ethnically stratified Twitter data as a surveillance indicator could inform epidemiologic trends to help estimate future surges of COVID-19 cases and potential future outbreaks of a pandemic among racial/ethnic groups.

Estimating the Best Time to View Cherry Blossoms Using Time-Series Forecasting Method

In recent years, tourist information collection using the internet has become common. Tourists are increasingly using internet resources to obtain tourist information. Social network service (SNS) users share tourist information of various kinds. Twitter, one SNS, has been used for many studies. We are pursuing research supporting a method using Twitter to help tourists obtain information: estimates of the best time to view cherry blossoms. Earlier studies have proposed a low-cost moving average method using geotagged tweets related to location information. Geotagged tweets are helpful as social sensors for real-time estimation and for the acquisition of local tourist information because the information can reflect real-world situations. Earlier studies have used weighted moving averages, indicating that a person can estimate the best time to view cherry blossoms in each prefecture. This study proposes a time-series prediction method using SNS data and machine learning as a new method for estimating the best times for viewing for a certain period. Combining the time-series forecasting method and the low-cost moving average method yields an estimate of the best time to view cherry blossoms. This report describes results confirming the usefulness of the proposed method by experimentation with estimation of the best time to view beautiful cherry blossoms in each prefecture and municipality.

A Method of Supplementing Reviews to Less-Known Tourist Spots Using Geotagged Tweets

When planning a travel or an adventure, sightseers increasingly rely on opinions posted on the Internet tourism related websites, such as TripAdvisor, Booking.com or Expedia. Unfortunately, beautiful, yet less-known places and rarely visited sightspots often do not accumulate sufficient number of valuable opinions on such websites. On the other hand, users often post their opinions on casual social media services, such as Facebook, Instagram or Twitter. Therefore, in this study, we develop a system for supplementing insufficient number of Internet opinions available for sightspots with tweets containing opinions of such sightspots, with a specific focus on wildlife sightspots. To do that, we develop an approach consisting of a system (PSRS) for wildlife sightspots and propose a method for verifying collected geotagged tweets and using them as on-spot reviews. Tweets that contain geolocation information are considered geotagged and therefore treated as possible tourist on-spot reviews. The main challenge, however, is to confirm the authenticity of the extracted tweets. Our method includes the use of location clustering and classification techniques. Specifically, extracted geotagged tweets are clustered by using location information and then annotated taking into consideration specific features applied to machine learning-based classification techniques. As for the machine learning (ML) algorithms, we adopt a fine-tuned transformer neural network-based BERT model which implements the information of token context orientation. The BERT model achieved a higher F-score of 0.936, suggesting that applying a state-of-the-art deep learning-based approach had a significant impact on solving this task. The extracted tweets and annotated scores are then mapped on the designed Park Supplementary Review System (PSRS) as supplementary reviews for travelers seeking additional information about the related sightseeing spots.

Spatiotemporal sentiment variation analysis of geotagged COVID-19 tweets from India using a hybrid deep learning model

India is a hotspot of the COVID-19 crisis. During the first wave, several lockdowns (L) and gradual unlock (UL) phases were implemented by the government of India (GOI) to curb the virus spread. These phases witnessed many challenges and various day-to-day developments such as virus spread and resource management. Twitter, a social media platform, was extensively used by citizens to react to these events and related topics that varied temporally and geographically. Analyzing these variations can be a potent tool for informed decision-making. This paper attempts to capture these spatiotemporal variations of citizen reactions by predicting and analyzing the sentiments of geotagged tweets during L and UL phases. Various sentiment analysis based studies on the related subject have been done; however, its integration with location intelligence for decision making remains a research gap. The sentiments were predicted through a proposed hybrid Deep Learning (DL) model which leverages the strengths of BiLSTM and CNN model classes. The model was trained on a freely available Sentiment140 dataset and was tested over manually annotated COVID-19 related tweets from India. The model classified the tweets with high accuracy of around 90%, and analysis of geotagged tweets during L and UL phases reveal significant geographical variations. The findings as a decision support system can aid in analyzing citizen reactions toward the resources and events during an ongoing pandemic. The system can have various applications such as resource planning, crowd management, policy formulation, vaccination, prompt response, etc.

Towards the Inference of Travel Purpose with Heterogeneous Urban Data

In people’s daily lives, travel takes up an important part, and many trips are generated everyday, such as going to school or shopping. With the widely adoption of GPS-integrated devices, a large amount of trips can be recorded with GPS trajectories. These trajectories are represented by sequences of geo-coordinates and can help us answer simple questions such as “where did you go”. However, there is another important question awaiting to be answered, that is “what did/will you do”, i.e., the trip purpose inference. In practice, people’s trip purposes are very important in understanding travel behaviors and estimating travel demands. Obviously, it is very challenging to infer trip purposes solely based on the trajectories, because the GPS devices are not accurate enough to pinpoint the venues visited. In this paper, we infer individual’s trip purposes by combining the knowledge from heterogeneous data sources including trajectories, POIs and social media data. The proposed Dynamic Bayesian Network model ( <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">DBN</i> ) captures three important factors: the sequential properties of trip activities, the functionality and POI popularity of trip end areas. In addition, we propose an efficient method with local candidate pools to identify POIs from geo-tagged social media messages, and learn the POI popularities from nearby social media data. Moreover, trip data is usually imbalanced across different activities. This data imbalance problem can cause serious challenges because the <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><b>DBN</b></i> model could be biased by those “popular” class labels. Considering this challenge, we propose an ensemble DBN method with sampling technique ( <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">eDBN</i> ) which results in more accurate inference. Furthermore, real-world trip data are continuously collected on a daily basis. The batch model would result in unnecessary computation because historical data need to be revisited. We handle this problem by proposing an incremental DBN method ( <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">iDBN</i> ) which is both effective and efficient. Extensive experiments are conducted on real-world data sets with trajectories of 8,361 residents and the 6.9 million geo-tagged tweets in the Bay area. Experimental results demonstrate the advantages of the proposed method on correctly inferring the trip purposes.

Individual Sensitivity to Change in the Lingua Franca Use of English

The study of ongoing change in English typically focuses on studying evidence from codified varieties of the language. Recent corpus studies show, however, that advanced non-native users of English may display heightened sensitivity to features undergoing frequency shifts similar to that experienced by native speakers. In addition, most studies aiming to detect patterns of linguistic regularity utilize large data sets that attempt to minimize the presence of the individual. In this study, we focus on change in ELF and place non-native individuals at the center of attention. Our empirical section examines how aggregated features that are currently undergoing change in codified varieties of English vary in the repertoires of ELF users of Twitter. To carry out this task, this study utilizes geo-tagged tweets retrieved from the Nordic Tweet Stream. The data obtained from this real-time monitor corpus are freely available for research and re-use athttps://cs.uef.fi/nts/. For the analysis itself, we selected the idiolects of 150 individual users who actively tweet in English from geographically varying locations in Finland. As American English predominates with several patterns of linguistic change in codified varieties of English, a simplified dichotomy between American and British features is utilized as a conceptual tool for inspecting variation. The idiolects are analyzed from the perspective of spelling and lexico-grammatical and morphological variation, such as V+ -ing|V + infinitive (e.g.start doing|start to do) and expanded predicates (e.g.take a look|have a look). The quantitative observations show that, particularly in the case of grammatical features, ELF speakers appear to have generally adhered to ongoing linguistic change.

Human movement patterns of different racial-ethnic and economic groups in U.S. top 50 populated cities: What can social media tell us about isolation?

ABSTRACT Many studies have proven that human movement patterns are strongly impacted by individual socioeconomic and demographic background. While many efforts have been made on exploring the influences of age and gender on movement patterns using social media, this study aims to analyse and compare the movement patterns among different racial-ethnic and economic groups using social media (i.e. geotagged tweets) from the U.S. top 50 populated cities. Results show that there are significant differences in number of activity zones and median travel distance across cities and demographic groups, and that power-laws tend to be captured in both spatial and demographic aspects. Additionally, the analysis of outbound-city travels demonstrates that some cities have slightly stronger interaction with others, and that economically disadvantaged populations and racial-ethnic minorities are more restricted in long distance travels, indicating that their spatial mobility is more limited to the local scale. Lastly, an economically-segregated movement pattern is discovered – upper-class neighbourhoods are mostly visited by the upper-class, while lower-class neighbourhoods are mainly accessed by the lower-class – but some racial-ethnic groups can diversify this segregated pattern in the local scale.

An Approach of Analyzing Movement Patterns Using Word Embeddings from Geo-tagged Tweets

An Approach of Analyzing Movement Patterns Using Word Embeddings from Geo-tagged Tweets

The times, they are a-changin’: tracking shifts in mental health signals from early phase to later phase of the COVID-19 pandemic in Australia

IntroductionWidespread problems of psychological distress have been observed in many countries following the outbreak of COVID-19, including Australia. What is lacking from current scholarship is a national-scale assessment that tracks...

Inquest of Current Situation in Afghanistan Under Taliban Rule Using Sentiment Analysis and Volume Analysis

Microblogging websites and social media platforms serve as a potential source for mining public opinions and sentiments on a variety of subjects including the prevailing situations in war-afflicted countries. In particular, Twitter has a large number of geotagged tweets that make the analysis of sentiments across time and space possible. This study performs volume analysis and sentiment analysis using LDA (Latent Dirichlet Allocation) and text mining over two datasets collected for different periods. To increase the adequacy and efficacy of the sentiment analysis, a hybrid feature engineering approach is proposed that elevates the performance of machine learning models. Geotagged tweets are used for volume analysis indicating that the highest number of tweets is originated from India, the US, the UK, Pakistan, and Afghanistan. Analysis of positive and negative tweets reveals that negative tweets are mostly originated from India and the US. On the contrary, positive tweets belong to Pakistan and Afghanistan. LDA is used for topic modeling on two datasets containing tweets about the current situation after the Taliban take control of Afghanistan. Topics extracted through LDA suggest that majority of the Afghanistan people seem satisfied with the Taliban’s takeover while the topics from negative tweets reveal that issues discussed in negative tweets are related to the US concerns in Afghanistan. Sentiment analysis over two different datasets indicates that the trend of the sentiments has been shifted positively over three weeks.

SHEDR: An End-to-End Deep Neural Event Detection and Recommendation Framework for Hyperlocal News Using Social Media

Residents often rely on newspapers and television to gather hyperlocal news for community awareness and engagement. More recently, social media have emerged as an increasingly important source of hyperlocal news. Thus far, the literature on using social media to create desirable societal benefits, such as civic awareness and engagement, is still in its infancy. One key challenge in this research stream is to timely and accurately distill information from noisy social media data streams to community members. In this work, we develop SHEDR (social media–based hyperlocal event detection and recommendation), an end-to-end neural event detection and recommendation framework with a particular use case for Twitter to facilitate residents’ information seeking of hyperlocal events. The key model innovation in SHEDR lies in the design of the hyperlocal event detector and the event recommender. First, we harness the power of two popular deep neural network models, the convolutional neural network (CNN) and long short-term memory (LSTM), in a novel joint CNN-LSTM model to characterize spatiotemporal dependencies for capturing unusualness in a region of interest, which is classified as a hyperlocal event. Next, we develop a neural pairwise ranking algorithm for recommending detected hyperlocal events to residents based on their interests. To alleviate the sparsity issue and improve personalization, our algorithm incorporates several types of contextual information covering topic, social, and geographical proximities. We perform comprehensive evaluations based on two large-scale data sets comprising geotagged tweets covering Seattle and Chicago. We demonstrate the effectiveness of our framework in comparison with several state-of-the-art approaches. We show that our hyperlocal event detection and recommendation models consistently and significantly outperform other approaches in terms of precision, recall, and F-1 scores. Summary of Contribution: In this paper, we focus on a novel and important, yet largely underexplored application of computing—how to improve civic engagement in local neighborhoods via local news sharing and consumption based on social media feeds. To address this question, we propose two new computational and data-driven methods: (1) a deep learning–based hyperlocal event detection algorithm that scans spatially and temporally to detect hyperlocal events from geotagged Twitter feeds; and (2) A personalized deep learning–based hyperlocal event recommender system that systematically integrates several contextual cues such as topical, geographical, and social proximity to recommend the detected hyperlocal events to potential users. We conduct a series of experiments to examine our proposed models. The outcomes demonstrate that our algorithms are significantly better than the state-of-the-art models and can provide users with more relevant information about the local neighborhoods that they live in, which in turn may boost their community engagement.

Work from home during the COVID-19 pandemic: An observational study based on a large geo-tagged COVID-19 Twitter dataset (UsaGeoCov19)

As COVID-19 swept over the world, people discussed facts, expressed opinions, and shared sentiments about the pandemic on social media. Since policies such as travel restriction and lockdown in reaction to COVID-19 were made at different levels of the society (e.g., schools and employers) and the government, we build a large geo-tagged Twitter dataset titled UsaGeoCov19 and perform an exploratory analysis by geographic location. Specifically, we collect 650,563 unique geo-tagged tweets across the United States covering the date range from January 25 to May 10, 2020. Tweet locations enable us to conduct region-specific studies such as tweeting volumes and sentiment, sometimes in response to local regulations and reported COVID-19 cases. During this period, many people started working from home. The gap between workdays and weekends in hourly tweet volumes inspire us to propose algorithms to estimate work engagement during the COVID-19 crisis. This paper also summarizes themes and topics of tweets in our dataset using both social media exclusive tools (i.e., #hashtags, @mentions) and the latent Dirichlet allocation model. We welcome requests for data sharing and conversations for more insights.UsaGeoCov19 link:http://yunhefeng.me/geo-tagged_twitter_datasets/.