Geotagged Twitter Data Research Articles

A name‐led approach to profile urban places based on geotagged Twitter data

AbstractPlace is a concept that is fundamental to how we orientate and communicate space in our everyday lives. Crowdsourced social media data present a valuable opportunity to develop bottom‐up inferences of places that are integral to social activities and settings. Conventional location‐led approaches use a predefined spatial unit to associate data and space with places, which cannot capture the richness of urban places (i.e., spatial extents and their dynamic functions). This article develops a name‐led framework to overcome these limitations in using social media data to study urban places. The framework first derives place names from georeferenced Twitter data combining text mining and spatial point pattern analysis, then estimates the spatial extents by spatial clustering, and further extracts their dynamic functions with time, which makes up a complete place profile. The framework is tested on a case study in Camden Borough, London and the results are evaluated through comparisons to the Foursquare point of interest data. This name‐led approach enables the shift from space‐based analysis to place‐based analysis of urban space.

EXAMINING ASSOCIATIONS OF THE SOCIOECONOMIC CHARACTERISTICS WITH THE NUMBER OF GEO-TAGGED TWEETS IN CENSUS BLOCK LEVEL (CASE STUDY: BOSTON)

Abstract. In this study, the aim is to help uncover some facts about who the Twitter users really are. To this purpose, geotagged twitter data from the city of Boston together with socio-economic data were used. In the first step, tweets in each census block were counted and using the Getis-Ord Gi* index the hotspots and coldspots of tweet locations were extracted. Then, a multiple linear regression was employed, having the number of tweets as the response variable and the population data, age, education, occupation and income as the explanatory variables. Hence, more insight into the relationship between the number of tweets and some socio-economic factors is obtained. Results show that the central parts of Boston are the hotspot and the southern areas are the coldspot locations with regard to tweet numbers. The regression results imply that the number of tweets shared by users in an area is related to the income, the number of people having a university degree and the number of people having each type of job in that spatial unit. The results achieved in this paper could lead to a better vision and understanding in analyzing the tweeter users’ behavior in any area of research and application.

Exploring geospatial characteristics of hashtag activism in Ferguson, Missouri: An application of social disorganization theory

Following the shooting of Michael Brown in 2014, a series of social protests on the streets and social media were ignited. The current research draws upon social disorganization theory to explore the geospatial patterns of Twitter activity related to the Michael Brown case across the state of Missouri. Geotagged Twitter data and census tract level American Community Survey data were used to determine if neighborhoods with greater social disadvantage were more represented in political discourse regarding police brutality. Results indicated wealthier neighborhoods with a higher percentage of black residents were more likely to engage in Twitter activity related to the Michael Brown case. A higher volume of activity was found, however, in more disadvantaged neighborhoods with little effect as to the percentage of black residents. Within a social disorganization framework, findings support the potential for future research to examine the idea that marginalized neighborhoods use social media as an outlet for their concerns about criminal justice practices.

Use of Twitter data to improve Zika virus surveillance in the United States during the 2016 epidemic

BackgroundZika virus (ZIKV) is an emerging mosquito-borne arbovirus that can produce serious public health consequences. In 2016, ZIKV caused an epidemic in many countries around the world, including the United States. ZIKV surveillance and vector control is essential to combating future epidemics. However, challenges relating to the timely publication of case reports significantly limit the effectiveness of current surveillance methods. In many countries with poor infrastructure, established systems for case reporting often do not exist. Previous studies investigating the H1N1 pandemic, general influenza and the recent Ebola outbreak have demonstrated that time- and geo-tagged Twitter data, which is immediately available, can be utilized to overcome these limitations.MethodsIn this study, we employed a recently developed system called Cloudberry to filter a random sample of Twitter data to investigate the feasibility of using such data for ZIKV epidemic tracking on a national and state (Florida) level. Two auto-regressive models were calibrated using weekly ZIKV case counts and zika tweets in order to estimate weekly ZIKV cases 1 week in advance.ResultsWhile models tended to over-predict at low case counts and under-predict at extreme high counts, a comparison of predicted versus observed weekly ZIKV case counts following model calibration demonstrated overall reasonable predictive accuracy, with an R2 of 0.74 for the Florida model and 0.70 for the U.S. model. Time-series analysis of predicted and observed ZIKV cases following internal cross-validation exhibited very similar patterns, demonstrating reasonable model performance. Spatially, the distribution of cumulative ZIKV case counts (local- & travel-related) and zika tweets across all 50 U.S. states showed a high correlation (r = 0.73) after adjusting for population.ConclusionsThis study demonstrates the value of utilizing Twitter data for the purposes of disease surveillance. This is of high value to epidemiologist and public health officials charged with protecting the public during future outbreaks.

A combination of incidence data and mobility proxies from social media predicts the intra-urban spread of dengue in Yogyakarta, Indonesia.

Only a few studies have investigated the potential of using geotagged social media data for predicting the patterns of spatio-temporal spread of vector-borne diseases. We herein demonstrated the role of human mobility in the intra-urban spread of dengue by weighting local incidence data with geo-tagged Twitter data as a proxy for human mobility across 45 neighborhoods in Yogyakarta city, Indonesia. To estimate the dengue virus importation pressure in each study neighborhood monthly, we developed an algorithm to estimate a dynamic mobility-weighted incidence index (MI), which quantifies the level of exposure to virus importation in any given neighborhood. Using a Bayesian spatio-temporal regression model, we estimated the coefficients and predictiveness of the MI index for lags up to 6 months. Specifically, we used a Poisson regression model with an unstructured spatial covariance matrix. We compared the predictability of the MI index to that of the dengue incidence rate over the preceding months in the same neighborhood (autocorrelation) and that of the mobility information alone. We based our estimates on a volume of 1·302·405 geotagged tweets (from 118·114 unique users) and monthly dengue incidence data for the 45 study neighborhoods in Yogyakarta city over the period from August 2016 to June 2018. The MI index, as a standalone variable, had the highest explanatory power for predicting dengue transmission risk in the study neighborhoods, with the greatest predictive ability at a 3-months lead time. The MI index was a better predictor of the dengue risk in a neighborhood than the recent transmission patterns in the same neighborhood, or just the mobility patterns between neighborhoods. Our results suggest that human mobility is an important driver of the spread of dengue within cities when combined with information on local circulation of the dengue virus. The geotagged Twitter data can provide important information on human mobility patterns to improve our understanding of the direction and the risk of spread of diseases, such as dengue. The proposed MI index together with traditional data sources can provide useful information for the development of more accurate and efficient early warning and response systems.

Mapping Consumer Sentiment Toward Wireless Services Using Geospatial Twitter Data

Hyper-dense wireless network deployment is one of the popular solutions to meeting high capacity requirement for 5G delivery. However, current operator understanding of consumer satisfaction comes from call centers and base station quality-of-service (QoS) reports with poor geographic accuracy. The dramatic increase in geo-tagged social media posts adds a new potential to understand consumer satisfaction towards target-specific quality-of-experience (QoE) topics. In our paper, we focus on evaluating users’ opinion on wireless service-related topics by applying natural language processing (NLP) to geo-tagged Twitter data. Current generalized sentiment detection methods with generalized NLP corpora are not topic specific. Here, we develop a novel wireless service topic-specific sentiment framework, yielding higher targeting accuracy than generalized NLP frameworks. To do so, we first annotate a new sentiment corpus called SignalSentiWord (SSW) and compare its performance with two other popular corpus libraries, AFINN and SentiWordNet. We then apply three established machine learning methods, namely: Naive Bayes (NB), Support Vector Machine (SVM), and Recurrent Neural Network (RNN) to build our topic-specific sentiment classifier. Furthermore, we discuss the capability of SSW to filter noisy and high-frequency irrelevant words to improve the performance of machine learning algorithms. Finally, the real-world testing results show that our proposed SSW improves the performance of NLP significantly.

Exploring the spatial distribution of geo-tagged Twitter feeds via street-centrality measures

The socio-spatial complexity of urban spaces is increasing with the broad reach of mobile devices and digital communication mediums. This research explores the quantifiable spatial distribution of urban activities through the lens of social media. Accordingly, two key objectives are addressed in this paper. First, testing the reliability of social media as a tool for understanding urban public activities; and second, exploring the effects of physical accessibility on the interactions of people with urban spaces. Furthermore, this study explores new methodological possibilities for reading urban space through social media and measurable accessibility. Three layers of data are used to address these objectives: a collection of geo-tagged public Twitter feeds, a geo-tagged name-generator survey, and the metric Euclidian centrality measures of the urban spatial network (closeness and betweenness). The findings show that the geo-tagged Twitter data can be a reliable tool for understanding the socio-spatial structure of urban public spaces. Results also suggest a variety of socio-spatial patterns arising from relating Twitter data to centrality measures with more emphasis on locality.

IMPROVED CLASSIFICATION OF SATELLITE IMAGERY USING SPATIAL FEATURE MAPS EXTRACTED FROM SOCIAL MEDIA

Abstract. In this work, we consider the exploitation of social media data in the context of Remote Sensing and Spatial Information Sciences. To this end, we explore a way of augmenting and integrating information represented by geo-located feature vectors into a system for the classification of satellite images. For that purpose, we present a quite general data fusion framework based on Convolutional Neural Network (CNN) and an initial examination of our approach on features from geo-located social media postings on the Twitter and Sentinel images. For this examination, we selected six simple Twitter features derived from the metadata, which we believe could contain information for the spatial context. We present initial experiments using geotagged Twitter data from Washington DC and Sentinel images showing this area. The goal of classification is to determine local climate zones (LCZ). First, we test whether our selected feature maps are not correlated with the LCZ classification at the geo-tag position. We apply a simple boost tree classifier on this data. The result turns out not to be a mere random classifier. Therefore, this data can be correlated with LCZ. To show the improvement by our method, we compare classification with and without the Twitter feature maps. In our experiments, we apply a standard pixel-based CNN classification of the Sentinel data and use it as a baseline model. After that, we expand the input augmenting additional Twitter feature maps within the CNN and assess the contribution of these additional features to the overall F1-score of the classification, which we determine from spatial cross-validation.

A year in Madrid as described through the analysis of geotagged Twitter data

Gaining a complete picture of the activity in a city using vast data sources is challenging yet potentially very valuable. One such source of data is Twitter which generates millions of short spatio-temporally localized messages that, as a collection, have information on city regions and many forms of city activity. The quantity of data, however, necessitates summarization in a way that makes consumption by an observer efficient, accurate, and comprehensive. We present a two-step process for analyzing geotagged twitter data within a localized urban environment. The first step involves an efficient form of latent Dirichlet allocation, using an expectation maximization, for topic content summarization of the text information in the tweets. The second step involves spatial and temporal analysis of information within each topic using two complimentary metrics. These proposed metrics characterize the distributional properties of tweets in time and space for all topics. We integrate the second step into a graphical user interface that enables the user to adeptly navigate through the space of hundreds of topics. We present results of a case study of the city of Madrid, Spain, for the year 2011 in which both large-scale protests and elections occurred. Our data analysis methods identify these important events, as well as other classes of more mundane routine activity and their associated locations in Madrid.

Geotagged US Tweets as Predictors of County-Level Health Outcomes, 2015-2016.

To leverage geotagged Twitter data to create national indicators of the social environment, with small-area indicators of prevalent sentiment and social modeling of health behaviors, and to test associations with county-level health outcomes, while controlling for demographic characteristics. We used Twitter's streaming application programming interface to continuously collect a random 1% subset of publicly available geo-located tweets in the contiguous United States. We collected approximately 80 million geotagged tweets from 603 363 unique Twitter users in a 12-month period (April 2015-March 2016). Across 3135 US counties, Twitter indicators of happiness, food, and physical activity were associated with lower premature mortality, obesity, and physical inactivity. Alcohol-use tweets predicted higher alcohol-use-related mortality. Social media represents a new type of real-time data that may enable public health officials to examine movement of norms, sentiment, and behaviors that may portend emerging issues or outbreaks-thus providing a way to intervene to prevent adverse health events and measure the impact of health interventions.

Using GPS Geo-tagged Social Media Data and Geodemographics to Investigate Social Differences: A Twitter Pilot Study

This article outlines a new method for investigating social position through geo-tagged Twitter data, specifically through the application of the geodemographic classification system Mosaic. The method involves the identification of a given tweeter’s likely location of residence from the ‘geo-tag’ attached to their tweet. Using this high-resolution geographic information, each individual tweet is then attributed a geodemographic classification. This article shows that the specific application of geodemographics for discerning between different types of tweeters is problematic in some ways, but that the general process of classifying tweeters according to their position in geographical space is viable and represents a powerful new method for discerning the social position of tweeters. Further research is required in this area, as there is great potential in employing the mobile global positioning system data appended to digital by-product data to explore the intersections between geographical space and social position.

A Spatiotemporal Analysis of Participatory Sensing Data 'Tweets' and Extreme Climate Events Toward Real-Time Urban Risk Management

Real-time urban climate monitoring provides useful information that can be utilized to help monitor and adapt to extreme events, including urban heatwaves. Typical approaches to the monitoring of climate data include the acquisition of weather station monitoring and also remote sensing via satellite sensors. However, climate monitoring stations are very often distributed spatially in a sparse manner, and consequently, this has a significant impact on the ability to reveal exposure risks due to extreme climates at an intra-urban scale (e.g., street level). Additionally, such traditional remote sensing data sources are typically not received and analyzed in realtime which is often required for adaptive urban management of climate extremes, such as sudden heatwaves. Fortunately, recent social media, such as Twitter, furnishes real-time and high-resolution spatial information that might be useful for climate condition estimation. The objective of this study is utilizing geo-tagged tweets (participatory sensing data) for urban temperature analysis. We first detect tweets relating hotness (hot-tweets). Then, we study relationships between monitored temperatures and hot-tweets via a statistical model framework based on copula modelling methods. We demonstrate that there are strong relationships between “hot-tweets” and temperatures recorded at an intra-urban scale, that we reveal in our analysis of Tokyo city and its suburbs. Subsequently, we then investigate the application of “hot-tweets” informing spatio-temporal Gaussian process interpolation of temperatures as an application example of “hot-tweets”. We utilize a combination of spatially sparse weather monitoring sensor data, infrequently available MODIS remote sensing data and spatially and temporally dense lower quality geo-tagged twitter data. Here, a spatial best linear unbiased estimation (S-BLUE) technique is applied. The result suggests that tweets provide some useful auxiliary information for urban climate assessment. Lastly, effectiveness of tweets toward a real-time urban risk management is discussed based on the analysis of the results.

Uncovering wireless blackspots using Twitter data

Blackspots are areas of poor signal coverage or service delivery that leads to customer complaints and loss in business revenue. Understanding their spatial–temporal patterns at a high resolution is important for interventions. Conventional methods such as customer helplines, drive-by testing, and network analysis tools often lack the real-time capability and spatial accuracy required. The potential of utilising geo-tagged Twitter data to uncover blackspots is investigated. Lexicon and machine-learning natural language processing techniques are applied to over 1.4 million Tweets in London to uncover blackspots for both pre-4G (2012) and post-4G (2016) roll out. It was found that long-term poor signal complaints make up the majority of complaints (86%) pre-4G roll out, but short-term network failure was responsible for most complaints (66%) post-4G roll out.

Contribution of geotagged Twitter data in the study of a social group’s activity space

Since 2009, the social media Twitter provides free access to localization data consisting of geotagged messages sent on the platform. We used this data to highlight their potential contributions to the study of social groups’ activity space. Using a sample of luxury shoppers, we analyzed the daily activity and mobility patterns of the upper middle class in Delhi, India. We intersected these data with the results of an ethnographic study carried out in two luxury shopping places in Delhi and found that the lower middle class was overrepresented in the Twitter sample. We argue that the varying motivation to post on social media tend to skew the representativeness of social groups sampled on a spatial criterion. We eventually advocate the complementary use of geotagged social media data and qualitative data based on ethnographic research.

Deriving retail centre locations and catchments from geo-tagged Twitter data

This investigation offers an initial foray into the application of geo-tagged Twitter data for generating insights within two areas of retail geography: establishing retail centre locations and defining catchment areas. Retail related Tweets were identified and their spatial attributes examined with an adaptive kernel density estimation, revealing that retail related Twitter content can successfully locate areas of elevated retail activity, however, these are constrained by biases within the data. Methods must also account for the underlying geographic distribution of Tweets to detect these fluctuations. Additionally, geo-tagged Twitter data can be utilised to examine human mobility patterns in a retail centre context. The catchments constructed from the data highlight the importance of accessibility on flows between locations, which have implications for the likely commuting choices that may be involved in retail centre journey decision-making. These approaches demonstrate the potential applications for less conventional datasets, such as those derived from social media data, to previously under-researched areas.

Building a National Neighborhood Dataset From Geotagged Twitter Data for Indicators of Happiness, Diet, and Physical Activity.

BackgroundStudies suggest that where people live, play, and work can influence health and well-being. However, the dearth of neighborhood data, especially data that is timely and consistent across geographies, hinders understanding of the effects of neighborhoods on health. Social media data represents a possible new data resource for neighborhood research.ObjectiveThe aim of this study was to build, from geotagged Twitter data, a national neighborhood database with area-level indicators of well-being and health behaviors.MethodsWe utilized Twitter’s streaming application programming interface to continuously collect a random 1% subset of publicly available geolocated tweets for 1 year (April 2015 to March 2016). We collected 80 million geotagged tweets from 603,363 unique Twitter users across the contiguous United States. We validated our machine learning algorithms for constructing indicators of happiness, food, and physical activity by comparing predicted values to those generated by human labelers. Geotagged tweets were spatially mapped to the 2010 census tract and zip code areas they fall within, which enabled further assessment of the associations between Twitter-derived neighborhood variables and neighborhood demographic, economic, business, and health characteristics.ResultsMachine labeled and manually labeled tweets had a high level of accuracy: 78% for happiness, 83% for food, and 85% for physical activity for dichotomized labels with the F scores 0.54, 0.86, and 0.90, respectively. About 20% of tweets were classified as happy. Relatively few terms (less than 25) were necessary to characterize the majority of tweets on food and physical activity. Data from over 70,000 census tracts from the United States suggest that census tract factors like percentage African American and economic disadvantage were associated with lower census tract happiness. Urbanicity was related to higher frequency of fast food tweets. Greater numbers of fast food restaurants predicted higher frequency of fast food mentions. Surprisingly, fitness centers and nature parks were only modestly associated with higher frequency of physical activity tweets. Greater state-level happiness, positivity toward physical activity, and positivity toward healthy foods, assessed via tweets, were associated with lower all-cause mortality and prevalence of chronic conditions such as obesity and diabetes and lower physical inactivity and smoking, controlling for state median income, median age, and percentage white non-Hispanic.ConclusionsMachine learning algorithms can be built with relatively high accuracy to characterize sentiment, food, and physical activity mentions on social media. Such data can be utilized to construct neighborhood indicators consistently and cost effectively. Access to neighborhood data, in turn, can be leveraged to better understand neighborhood effects and address social determinants of health. We found that neighborhoods with social and economic disadvantage, high urbanicity, and more fast food restaurants may exhibit lower happiness and fewer healthy behaviors.

Estimating Mobile Traffic Demand Using Twitter

In this letter, the authors show that structured social media data can act as an accurate predictor for wireless data demand patterns at a high spatial-temporal resolution. A case-study is performed on Greater London covering a 5000 km $^{2}$ area. The data used includes over 0.6 million geo-tagged Twitter data, over 1 million mobile phone data demand records, and U.K. census data. The analysis shows that social media activity (Tweets/s ${n}$ ) can accurately predict the long-term traffic demand for both the uplink and downlink channels. The relationship between social media activity and traffic demand obeys a power law and the model explains for over 71%–79% of the variance in real traffic demand. This is a significant improvement over existing methods of long-term traffic prediction such as census population data ( $ {R^{2}=0.57}$ ). The authors also show that social media data can also forward predict short-term traffic demand for up to 2 h on the same day and for the same time in the following 2–3 days.

Leveraging geotagged Twitter data to examine neighborhood happiness, diet, and physical activity

ObjectivesUsing publicly available, geotagged Twitter data, we created neighborhood indicators for happiness, food and physical activity for three large counties: Salt Lake, San Francisco and New York. MethodsWe utilize 2.8 million tweets collected between February–August 2015 in our analysis. Geo-coordinates of where tweets were sent allow us to spatially join them to 2010 census tract locations. We implemented quality control checks and tested associations between Twitter-derived variables and sociodemographic characteristics. ResultsFor a random subset of tweets, manually labeled tweets and algorithm labeled tweets had excellent levels of agreement: 73% for happiness; 83% for food, and 85% for physical activity. Happy tweets, healthy food references, and physical activity references were less frequent in census tracts with greater economic disadvantage and higher proportions of racial/ethnic minorities and youths. ConclusionsSocial media can be leveraged to provide greater understanding of the well-being and health behaviors of communities—information that has been previously difficult and expensive to obtain consistently across geographies. More open access neighborhood data can enable better design of programs and policies addressing social determinants of health.

Understanding U.S. regional linguistic variation with Twitter data analysis

We analyze a Big Data set of geo-tagged tweets for a year (Oct. 2013–Oct. 2014) to understand the regional linguistic variation in the U.S. Prior work on regional linguistic variations usually took a long time to collect data and focused on either rural or urban areas. Geo-tagged Twitter data offers an unprecedented database with rich linguistic representation of fine spatiotemporal resolution and continuity. From the one-year Twitter corpus, we extract lexical characteristics for twitter users by summarizing the frequencies of a set of lexical alternations that each user has used. We spatially aggregate and smooth each lexical characteristic to derive county-based linguistic variables, from which orthogonal dimensions are extracted using the principal component analysis (PCA). Finally a regionalization method is used to discover hierarchical dialect regions using the PCA components. The regionalization results reveal interesting linguistic regional variations in the U.S. The discovered regions not only confirm past research findings in the literature but also provide new insights and a more detailed understanding of very recent linguistic patterns in the U.S.

격자기반 분석을 통한 위치기반 소셜 미디어 데이터와 부동산 가격지수 간의 공간적 상관성 분석 연구

본 연구에서는 위치기반 소셜 미디어 데이터의 공간적 분포가 지역별 부동산 지수와 어떠한 공간적 관련성을 가지는지에 대해 알아보고자 한다. 두 데이터는 상이한 자료 형식을 가지고 있어, 이를 보완할 수 있는 방법론으로 본 연구에서는 격자 기반의 공간분석 방법을 적용하였다. 대상 데이터로는 2013년 8월 한 달간의 지오태그된 트윗 데이터와 행정구역별 주택가격지수(매매, 전세)를 이용하였으며, 공간적 범위는 서울과 수도권 일부를 포함하도록 하였다. 두 데이터 간의 상이한 공간적 단위를 고려하여 2,000m 단위의 격자망을 구성하고 이에 맞게 두 데이터를 격자 데이터 형태로 변환하였다. 변환된 두 데이터에 대하여 Hot spot 분석을 실시하여 공간적 분포를 시각적으로 비교하였으며, 공간시차를 고려한 이변량 공간적 상관계수를 측정함으로써 정량적 분석을 실시하였다. 시각적, 정량적 분석 결과, 서초구 지역이 트윗 데이터와 주택매매가격지수 데이터에서 공통적인 Hotspot 지역으로 탐색되었으나 주택전세가격지수 데이터와는 뚜렷한 공간적 상관성이 탐색되지 않았다. In this study, the spatial relevance between the regional housing price data and the spatial distribution of the location-based social media data is explored. The spatial analysis with rasterization was applied to this study, because the both data have a different form to analyze. The geo-tagged Twitter data had been collected for a month and the regional housing price index about sales and lease were used. The spatial range of both data includes Seoul and the some parts of the metropolitan area. 2,000m grid was constructed to consider the different spatial measure between two data, and they were combined into the constructed grids. The Hotspot Analysis was operated using the combined dataset to see the comparison of spatial distribution, and the bivariate spatial correlation coefficients between two data were measured for the quantitative analysis. The result of this study shows that Seocho-gu area is detected as a common hotspot of tweet and housing sales price index data. though the spatial relevance is not detected between tweet and housing lease price index data.