Understanding demographic and socioeconomic biases of geotagged Twitter users at the county level

ABSTRACT

Massive social media data produced from microblog platforms provide a new data source for studying human dynamics at an unprecedented scale. Meanwhile, population bias in geotagged Twitter users is widely recognized. Understanding the demographic and socioeconomic biases of Twitter users is critical for making reliable inferences on the attitudes and behaviors of the population. However, the existing global models cannot capture the regional variations of the demographic and socioeconomic biases. To bridge the gap, we modeled the relationships between different demographic/socioeconomic factors and geotagged Twitter users for the whole contiguous United States, aiming to understand how the demographic and socioeconomic factors relate to the number of Twitter users at county level. To effectively identify the local Twitter users for each county of the United States, we integrate three commonly used methods and develop a query approach in a high-performance computing environment. The results demonstrate that we can not only identify how the demographic and socioeconomic factors relate to the number of Twitter users, but can also measure and map how the influence of these factors vary across counties.     

Visualizing spatiotemporal trajectories of mobile social media users using space–time cube

The implementation of social network applications on mobile platforms has significantly elevated the activity of mobile social networking. Mobile social networking offers a channel for recording an individual’s spatiotemporal behaviors when location-detecting capabilities of devices are enabled. It also facilitates the study of time geography on an individual level, which has previously suffered from a scarcity of georeferenced movement data. In this paper, we report on the use of georeferenced tweets to display and analyze the spatiotemporal patterns of daily user trajectories. For georeferenced tweets having both location information in longitude and latitude values and recorded creation time, we apply a space–time cube approach for visualization. Compared to the traditional methodologies for time geography studies such as the travel diary-based approach, the analytics using social media data present challenges broadly associated with those of Big Data, including the characteristics of high velocity, large volume, and heterogeneity. For this study, a batch processing system has been developed for extracting spatiotemporal information from each tweet and then creating trajectories of each individual mobile Twitter user. Using social media data in time geographic research has the benefits of study area flexibility, continuous observation and non-involvement with contributors. For example, during every 30-minute cycle, we collected tweets created by about 50,000 Twitter users living in a geographic region covering New York City to Washington, DC. Each tweet can indicate the exact location of its creator when the tweet was posted. Thus, the linked tweets show a Twitter users’ movement trajectory in space and time. This study explores using data intensive computing for processing Twitter data to generate spatiotemporal information that can recreate the space–time trajectories of their creators.     

Geo‐Social Model: A Conceptual Framework for Real‐time Geocollaboration

Synchronous geocollaboration helps geographically dispersed people to work together in a shared geospatial environment. Its real‐time nature, multiple users' interaction and diversity of work context impose some special social, organizational and technological requirements, making the development of such real‐time geocollaboration systems a challenging task. A conceptual framework is therefore needed to specify and describe what synchronous geocollaboration is, considering its social, spatial and technical aspects. The geo‐social model presented in this article describes a conceptual framework for synchronous geocollaboration systems addressing the above aspects, identifies the core elements of the system and describes how these elements collaborate with each other. This model is presented using application‐level ontology and is then applied to a multi‐agent system based prototype in which multiple users can interact and negotiate in a shared 3D geospatial environment.     

Crowdsourcing functions of the living city from Twitter and Foursquare data

ABSTRACT

Urban functions are closely related to people’s spatiotemporal activity patterns, transportation needs, and a city’s business distribution and development trends. Studies investigating urban functions have used different data sources, such as remotely sensed imageries, observation, photography, and cognitive maps. However, these data sources usually suffer from low spatial, temporal, and thematic resolution. This article attempts to investigate human activities to understand urban functions through crowdsourcing social media data. In this study, we mined Twitter and Foursquare data to extract and analyze six types of human activities. The spatiotemporal analysis revealed hotspots for different activity intensities at different temporal resolution. We also applied the classified model in a real-time system to extract information of various urban functions. This study demonstrates the significance and usefulness of social sensing in analyzing urban functions. By combining different platforms of social media data and analyzing people’s geo-tagged city experience, this article contributes to leverage voluntary local knowledge to better depict human dynamics, discover spatiotemporal city characteristics, and convey information about cities.     

Triangulating Social Multimedia Content for Event Localization using Flickr and Twitter

The analysis of social media content for the extraction of geospatial information and event‐related knowledge has recently received substantial attention. In this article we present an approach that leverages the complementary nature of social multimedia content by utilizing heterogeneous sources of social media feeds to assess the impact area of a natural disaster. More specifically, we introduce a novel social multimedia triangulation process that uses both Twitter and Flickr content in an integrated two‐step process: Twitter content is used to identify toponym references associated with a disaster; this information is then used to provide approximate orientation for the associated Flickr imagery, allowing us to delineate the impact area as the overlap of multiple view footprints. In this approach, we practically crowdsource approximate orientations from Twitter content and use this information to orient Flickr imagery accordingly and identify the impact area through viewshed analysis and viewpoint integration. This approach enables us to avoid computationally intensive image analysis tasks associated with traditional image orientation, while allowing us to triangulate numerous images by having them pointed towards the crowdsourced toponym location. The article presents our approach and demonstrates its performance using a real‐world wildfire event as a representative application case study.     

New data sources for social indicators: the case study of contacting politicians by Twitter

ABSTRACT

Data availability is a persistent constraint in social policy analysis. Web 2.0 technologies could provide valuable new data sources, but first, their potentials and limitations need to be investigated. This paper reports on a method using Twitter data for deriving indications of active citizenship, taken as an example of social indicators. Active citizenship is a dimension of social capital, empowering communities and reducing possibilities of social exclusion. However, classical measurements of active citizenship are generally costly and time-consuming. This paper looks at one of such classic indicators, namely, responses to the survey question ‘contacts to politicians’. It compares official survey results in Spain with findings from an analysis of Twitter data. Each method presents its own strengths and weakness, thus best results may be achieved by the combination of both. Official surveys have the clear advantage of being statistically robust and representative of a total population. Instead, Twitter data offer more timely and less costly information, with higher spatial and temporal resolution. This paper presents our full methodological workflow for analysing and comparing these two data sources. The research results advance the debate on how social media data could be mined for policy analysis.     

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

Place 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.     

Geo‐parsing Messages from Microtext

Widespread use of social media during crises has become commonplace, as shown by the volume of messages during the Haiti earthquake of 2010 and Japan tsunami of 2011. Location mentions are particularly important in disaster messages as they can show emergency responders where problems have occurred. This article explores the sorts of locations that occur in disaster‐related social messages, how well off‐the‐shelf software identifies those locations, and what is needed to improve automated location identification, called geo‐parsing. To do this, we have sampled Twitter messages from the February 2011 earthquake in Christchurch, Canterbury, New Zealand. We annotated locations in messages manually to make a gold standard by which to measure locations identified by a Named Entity Recognition software. The Stanford NER software found some locations that were proper nouns, but did not identify locations that were not capitalized, local streets and buildings, or non‐standard place abbreviations and mis‐spellings that are plentiful in microtext. We review how these problems might be solved in software research, and model a readable crisis map that shows crisis location clusters via enlarged place labels.     

Improving Large Area Population Mapping Using Geotweet Densities

Many different methods are used to disaggregate census data and predict population densities to construct finer scale, gridded population data sets. These methods often involve a range of high resolution geospatial covariate datasets on aspects such as urban areas, infrastructure, land cover and topography; such covariates, however, are not directly indicative of the presence of people. Here we tested the potential of geo‐located tweets from the social media application, Twitter, as a covariate in the production of population maps. The density of geo‐located tweets in 1x1 km grid cells over a 2‐month period across Indonesia, a country with one of the highest Twitter usage rates in the world, was input as a covariate into a previously published random forests‐based census disaggregation method. Comparison of internal measures of accuracy and external assessments between models built with and without the geotweets showed that increases in population mapping accuracy could be obtained using the geotweet densities as a covariate layer. The work highlights the potential for such social media‐derived data in improving our understanding of population distributions and offers promise for more dynamic mapping with such data being continually produced and freely available.     

A spatial‐temporal‐semantic approach for detecting local events using geo‐social media data

Social media networks allow users to post what they are involved in with location information in a real‐time manner. It is therefore possible to collect large amounts of information related to local events from existing social networks. Mining this abundant information can feed users and organizations with situational awareness to make responsive plans for ongoing events. Despite the fact that a number of studies have been conducted to detect local events using social media data, the event content is not efficiently summarized and/or the correlation between abnormal neighboring regions is not investigated. This article presents a spatial‐temporal‐semantic approach to local event detection using geo‐social media data. Geographical regularities are first measured to extract spatio‐temporal outliers, of which the corresponding tweet content is automatically summarized using the topic modeling method. The correlation between outliers is subsequently examined by investigating their spatial adjacency and semantic similarity. A case study on the 2014 Toronto International Film Festival (TIFF) is conducted using Twitter data to evaluate our approach. This reveals that up to 87% of the events detected are correctly identified compared with the official TIFF schedule. This work is beneficial for authorities to keep track of urban dynamics and helps build smart cities by providing new ways of detecting what is happening in them.     

Modeling Use of Space from Social Media Data Using a Biased Random Walker

Individuals and other entities move through space as a function of local characteristics of place, their internal behavioral models, and the topological structure of the underlying space. When a collection of locations (i.e. geotagged photos or other geotagged social media information) from a large number of individuals is assembled, it becomes possible to understand the interrelationship between the individuals and the space they occupy. This research systematically considers this interrelationship through an examination of the effect of the intersection of behavioral and spatial characteristics on individuals moving on street networks. The research illustrates how social media data, in combination with a biased random walker, can be used to understand and model the interaction of spatial structure and social‐environmental factors on influencing individuals' use of their environment. The biased walker offers a flexible approach to incorporate consideration of both social‐environmental and structural factors into a model and we demonstrate this through a case study wherein we are able to use the random walker to model the characteristics of Flickr users in New York City.     

NeuroTPR: A neuro‐net toponym recognition model for extracting locations from social media messages

Social media messages, such as tweets, are frequently used by people during natural disasters to share real‐time information and to report incidents. Within these messages, geographic locations are often described. Accurate recognition and geolocation of these locations are critical for reaching those in need. This article focuses on the first part of this process, namely recognizing locations from social media messages. While general named entity recognition tools are often used to recognize locations, their performance is limited due to the various language irregularities associated with social media text, such as informal sentence structures, inconsistent letter cases, name abbreviations, and misspellings. We present NeuroTPR, which is a Neuro‐net ToPonym Recognition model designed specifically with these linguistic irregularities in mind. Our approach extends a general bidirectional recurrent neural network model with a number of features designed to address the task of location recognition in social media messages. We also propose an automatic workflow for generating annotated data sets from Wikipedia articles for training toponym recognition models. We demonstrate NeuroTPR by applying it to three test data sets, including a Twitter data set from Hurricane Harvey, and comparing its performance with those of six baseline models.     

Inferring the Location of Twitter Messages Based on User Relationships

User interaction in social networks, such as Twitter and Facebook, is increasingly becoming a source of useful information on daily events. The online monitoring of short messages posted in such networks often provides insight on the repercussions of events of several different natures, such as (in the recent past) the earthquake and tsunami in Japan, the royal wedding in Britain and the death of Osama bin Laden. Studying the origins and the propagation of messages regarding such topics helps social scientists in their quest for improving the current understanding of human relationships and interactions. However, the actual location associated to a tweet or to a Facebook message can be rather uncertain. Some tweets are posted with an automatically determined location (from an IP address), or with a user‐informed location, both in text form, usually the name of a city. We observe that most Twitter users opt not to publish their location, and many do so in a cryptic way, mentioning non‐existing places or providing less specific place names (such as “Brazil”). In this article, we focus on the problem of enriching the location of tweets using alternative data, particularly the social relationships between Twitter users. Our strategy involves recursively expanding the network of locatable users using following‐follower relationships. Verification is achieved using cross‐validation techniques, in which the location of a fraction of the users with known locations is used to determine the location of the others, thus allowing us to compare the actual location to the inferred one and verify the quality of the estimation. With an estimate of the precision of the method, it can then be applied to locationless tweets. Our intention is to infer the location of as many users as possible, in order to increase the number of tweets that can be used in spatial analyses of social phenomena. The article demonstrates the feasibility of our approach using a dataset comprising tweets that mention keywords related to dengue fever, increasing by 45% the number of locatable tweets.     

Revisiting the death of geography in the era of Big Data: the friction of distance in cyberspace and real space

Many scholars have argued that the importance of geographic proximity in human interactions has been diminished by the use of the Internet, while others disagree with this argument. Studies have noted the distance decay effect in both cyberspace and real space, showing that interactions occur with an inverse relationship between the number of interactions and the distance between the locations of the interactors. However, these studies rarely provide strong evidence to show the influence of distance on interactions in cyberspace, nor do they quantify the differences in the amount of friction of distance between cyberspace and real space. To fill this gap, this study used massive amounts of social media data (Twitter) to compare the influence of distance decay on human interactions between cyberspace and real space in a quantitative manner. To estimate the distance decay effect in both cyberspace and real space, the distance decay function of interactions in each space was modeled. Estimating the distance decay in cyberspace in this study can help predict the degree of information flow across space through social media. Measuring how far ideas can be diffused through social media is useful for users of location-based services, policy advocates, public health officials, and political campaigners.     

Modeling Users' Behavior for Testing the Performance of a Web Map Tile Service

Web Map Tile Services (WMTS) are widely used in many fields to quickly and efficiently visualize geospatial data for public use. To ensure that a WMTS can successfully fulfill users' expectations and requirements, the performance of a service must be measured to track latencies and bottlenecks that may downgrade the overall quality of service (QoS). Traditional synthetic workloads used to evaluate WMTS applications are usually generated by repeated static URLs, through randomized requests, or by an access log replay. These three methods do not take request characteristics and users' behaviors into consideration, while access logs are not available for systems still under development. Thus, the evaluation outcomes obtained by these methods cannot represent the real performance of online WMTS applications. In this article a new workload model named HELP (Hotspot/think‐timE/Length/Path) is proposed to measure the performance of a prototype WMTS. This model describes how users browse a WMTS map and statistically characterizes complete map navigation behaviors. Then, the HELP model is implemented in HP LoadRunner and used to generate a synthetic workload to evaluate the target WMTS. Experimental results illustrate that the performance representation of the HELP workload is more accurate than that of the other two models, and how a bottleneck in the target system was identified. Additional statistical analysis of request logs and “hotspots” visualizations further validate the proposed HELP workload.     

Understanding Design with VGI using an Information Relevance Framework

Volunteered Geographic Information (VGI) has the potential to offer benefits to end‐users over and above those of Professional Geographic Information (PGI). A multi‐methods approach, consisting of participatory observation, focus groups and diary studies, was used to study how VGI and PGI were actually used by a target user group. A theoretical framework of information relevance was used to understand the attributes of information that were most important in relation to the characteristics of the users' activity and their community. The key finding was that the discussion amongst GIS designers should not be whether to choose VGI or PGI as the information data set, but to consider which combination of VGI and PGI relating to different geographic features and task characteristics would best meet the users' needs. VGI is likely to be most relevant to the user when a geographic feature is dynamic rather than static in nature, and can also provide a level of detail that is unlikely to arise through PGI. These findings have implications for how different forms of information are most effective for different usage situations. Above all, a case is presented for the implementation of User Centred Design (UCD) principles when integrating VGI and PGI together in a single mashup‐based product.     

Los Angeles as a digital place: The geographies of user‐generated content

Online representations of places are becoming pivotal in informing our understanding of urban life. Content production on online platforms is grounded in the geography of their users and their digital infrastructure. These constraints shape place representation, that is, the amount, quality, and type of digital information available in a geographic area. In this article we study the place representation of user‐generated content (UGC) in Los Angeles County, relating the spatial distribution of the data to its geo‐demographic context. Adopting a comparative and multi‐platform approach, this quantitative analysis investigates the spatial relationship between four diverse UGC datasets and their context at the census tract level (about 685,000 geo‐located tweets, 9,700 Wikipedia pages, 4 million OpenStreetMap objects, and 180,000 Foursquare venues). The context includes the ethnicity, age, income, education, and deprivation of residents, as well as public infrastructure. An exploratory spatial analysis and regression‐based models indicate that the four UGC platforms possess distinct geographies of place representation. To a moderate extent, the presence of Twitter, OpenStreetMap, and Foursquare data is influenced by population density, ethnicity, education, and income. However, each platform responds to different socio‐economic factors and clusters emerge in disparate hotspots. Unexpectedly, Twitter data tend to be located in denser, more deprived areas, and the geography of Wikipedia appears peculiar and harder to explain. These trends are compared with previous findings for the area of Greater London.     

Detecting Non‐personal and Spam Users on Geo‐tagged Twitter Network

With the rapid growth and popularity of mobile devices and location‐aware technologies, online social networks such as Twitter have become an important data source for scientists to conduct geo‐social network research. Non‐personal accounts, spam users and junk tweets, however, pose severe problems to the extraction of meaningful information and the validation of any research findings on tweets or twitter users. Therefore, the detection of such users is a critical and fundamental step for twitter‐related geographic research. In this study, we develop a methodological framework to: (1) extract user characteristics based on geographic, graph‐based and content‐based features of tweets; (2) construct a training dataset by manually inspecting and labeling a large sample of twitter users; and (3) derive reliable rules and knowledge for detecting non‐personal users with supervised classification methods. The extracted geographic characteristics of a user include maximum speed, mean speed, the number of different counties that the user has been to, and others. Content‐based characteristics for a user include the number of tweets per month, the percentage of tweets with URLs or Hashtags, and the percentage of tweets with emotions, detected with sentiment analysis. The extracted rules are theoretically interesting and practically useful. Specifically, the results show that geographic features, such as the average speed and frequency of county changes, can serve as important indicators of non‐personal users. For non‐spatial characteristics, the percentage of tweets with a high human factor index, the percentage of tweets with URLs, and the percentage of tweets with mentioned/replied users are the top three features in detecting non‐personal users.     

A graph-based approach to detecting tourist movement patterns using social media data

ABSTRACT

Understanding the characteristics of tourist movement is essential for tourist behavior studies since the characteristics underpin how the tourist industry management selects strategies for attraction planning to commercial product development. However, conventional tourism research methods are not either scalable or cost-efficient to discover underlying movement patterns due to the massive datasets. With advances in information and communication technology, social media platforms provide big data sets generated by millions of people from different countries, all of which can be harvested cost efficiently. This paper introduces a graph-based method to detect tourist movement patterns from Twitter data. First, collected tweets with geo-tags are cleaned to filter those not published by tourists. Second, a DBSCAN-based clustering method is adapted to construct tourist graphs consisting of the tourist attraction vertices and edges. Third, network analytical methods (e.g. betweenness centrality, Markov clustering algorithm) are applied to detect tourist movement patterns, including popular attractions, centric attractions, and popular tour routes. New York City in the United States is selected to demonstrate the utility of the proposed methodology. The detected tourist movement patterns assist business and government activities whose mission is tour product planning, transportation, and development of both shopping and accommodation centers.     

A Location Aware Mobile Tool for Direct and Indirect Climate Data Sensors

Access to GIS data from mobile platforms continues to be a challenge and there is a wide range of fields where it is extremely useful. In this work, we combined three key aspects: climate data sensors, mobile platforms and spatial proximity operations. We published and made use of a web 2.0 network of climate data, where content is user‐collected, by means of their meteorological stations, and exposed as available information for the virtual community. Moreover, we enriched this data by giving the users the opportunity to directly inform the system with different climate measures. In general, management of this type of information from a mobile application could result in an important decision tool, as it enables us to provide climate‐related data according to a context and a geographical location. Therefore, we implemented a native mobile application for iPhone and iPad platforms by using ArcGIS SDK for iOS and by integrating a series of ArcGIS webmaps, which allows us to perform geospatial queries based on the user's location, offering, at the same time, access to all the data provided by the climate data sensor network and from direct users.