Geo-social Data Research Articles

Advanced computing model for geosocial media using big data analytics

Social media has drastically entered into a new concept by empowering people to publish their data along with their locations in order to provide benefits to the community and the country overall. There is a significant increase in the use of geosocial networks, such as Twitter, Facebook, Foursquare, and Flickr. Therefore, people worldwide can now voice their opinion, report an event instantly, and connect with others while sharing their views. Thus, geosocial network data provides full information on human current trends in terms of behavior, lifestyle, incidents and events, disasters, current medical infections, and much more with respect to location. Hence, current geosocial media can serve as data assets for countries and their government by analyzing geosocial data in a real time. However, there are millions of geosocial network users who generate terabytes of heterogeneous data with a variety of information every day and at high speed; such information is called “Big Data.” Analyzing such a significant amount of data and making real-time decisions regarding event detection is a challenging task. Therefore, in this paper, we propose an efficient system for exploring geosocial networks while harvesting data in order to make real-time decisions while detecting various events. A novel system architecture is proposed and implemented in a real environment in order to process an abundant amount of various social network data to monitor Earth events, incidents, medical diseases, user trends, and views to make future real-time decisions and facilitate future planning. The proposed system consists of five layers, i.e., data collection, data processing, application, communication, and data storage. The system deploys Spark at the top of the Hadoop ecosystem to run a real-time analysis. Twitter and Flickr data are analyzed using the proposed architecture in order to identify current events or disasters, such as earthquakes, fires, Ebola virus contagion, and snow. The system is evaluated on the Tweeter’s data by considering the recent earthquake detection occurred in New Zealand. The system is also evaluated with respect to efficiency while considering system throughput on large datasets. We prove that the system has higher throughput and is capable of analyzing a huge amount of geosocial network data at a real time while detecting any event.

Combined geo-social search: computing top-k join queries over incomplete information

Geo-social data sets, which fuse the social and the geospatial facets of data, are vibrant data sources that associate people and activities with locations. In a combined geo-social search, several search queries are posed over geospatial and social data sources, or over data sources with both geospatial and social facets; and the search results, provided as ranked lists of items, are integrated by associating matching items, yielding combinations. Each combination has a score which is a function of the scores of the items it comprises, and the goal is to compute the k combinations with the highest score, that is, the top-k combinations. However, since geo-social data sources are heterogeneous, data items may not have matching items in all the ranked lists. Such items cannot be included in complete combinations. Hence, we study the approach where combinations are padded by nulls for missing items, as in outer-join. A combination is maximal if it cannot be extended by replacing a null by an item. We show that if some of the top-k maximal combinations contain null values, the computation requires reading entire lists, and hence, traditional top-k algorithms and optimization techniques are not as effective as in the case of an ordinary top-k join. Thus, we present two novel algorithms for computing the top-k maximal combinations. One novel algorithm is instance optimal over the class of algorithms that compute a 𝜃-approximation to the answer. The second algorithm is more efficient than the modification of two common top-k algorithms to compute maximal combinations. We show this analytically, and experimentally over real and synthetic data.

Uncertainty in geosocial data

In data management, uncertainty and lack of information are commonly considered as hurdles to overcome. But when it comes to management of geosocial data, where data can be used to associate people with geographic locations they visited, uncertainty is frequently not just an obstacle but also a desired feature. Uncertainty and lack of information---such as knowing only approximate locations of users or knowing only some of the locations users visited---may reduce the accuracy of data analysis. They, however, may be desired, or even required, for keeping user privacy, and for using data that otherwise would not have been collected and used. Due to the heterogeneity of geosocial data, uncertainty is prevalent in geosocial applications, and should not be overlooked. In this paper, we discuss some of the causes of uncertainty in geosocial data management. We elaborate on some of the advantages and disadvantages of using inaccurate or incomplete geosocial data, and we illustrate some of the methods to cope with uncertainty in geosocial applications.

A THREE-STEP SPATIAL-TEMPORAL-SEMANTIC CLUSTERING METHOD FOR HUMAN ACTIVITY PATTERN ANALYSIS

How people move in cities and what they do in various locations at different times form human activity patterns. Human activity pattern plays a key role in in urban planning, traffic forecasting, public health and safety, emergency response, friend recommendation, and so on. Therefore, scholars from different fields, such as social science, geography, transportation, physics and computer science, have made great efforts in modelling and analysing human activity patterns or human mobility patterns. One of the essential tasks in such studies is to find the locations or places where individuals stay to perform some kind of activities before further activity pattern analysis. <br><br> In the era of Big Data, the emerging of social media along with wearable devices enables human activity data to be collected more easily and efficiently. Furthermore, the dimension of the accessible human activity data has been extended from two to three (space or space-time) to four dimensions (space, time and semantics). More specifically, not only a location and time that people stay and spend are collected, but also what people “say” for in a location at a time can be obtained. The characteristics of these datasets shed new light on the analysis of human mobility, where some of new methodologies should be accordingly developed to handle them. <br><br> Traditional methods such as neural networks, statistics and clustering have been applied to study human activity patterns using geosocial media data. Among them, clustering methods have been widely used to analyse spatiotemporal patterns. However, to our best knowledge, few of clustering algorithms are specifically developed for handling the datasets that contain spatial, temporal and semantic aspects all together. In this work, we propose a three-step human activity clustering method based on space, time and semantics to fill this gap. One-year Twitter data, posted in Toronto, Canada, is used to test the clustering-based method. The results show that the approximate 55% spatiotemporal clusters distributed in different locations can be eventually grouped as the same type of clusters with consideration of semantic aspect.

Understanding Public Opinions from Geosocial Media

Increasingly, social media data are linked to locations through embedded GPS coordinates. Many local governments are showing interest in the potential to repurpose these firsthand geo-data to gauge spatial and temporal dynamics of public opinions in ways that complement information collected through traditional public engagement methods. Using these geosocial data is not without challenges since they are usually unstructured, vary in quality, and often require considerable effort to extract information that is relevant to local governments’ needs from large data volumes. Understanding local relevance requires development of both data processing methods and their use in empirical studies. This paper addresses this latter need through a case study that demonstrates how spatially-referenced Twitter data can shed light on citizens’ transportation and planning concerns. A web-based toolkit that integrates text processing methods is used to model Twitter data collected for the Region of Waterloo (Ontario, Canada) between March 2014 and July 2015 and assess citizens’ concerns related to the planning and construction of a new light rail transit line. The study suggests that geosocial media can help identify geographies of public perceptions concerning public facilities and services and have potential to complement other methods of gauging public sentiment.

Geo-Social K-Cover Group Queries for Collaborative Spatial Computing

With the rapid development of location-aware mobile devices, ubiquitous Internet access and social computing technologies, lots of users’ personal information, such as location data and social data, has been readily accessible from various mobile platforms and online social networks. The convergence of these two types of data, known as geo-social data , has enabled collaborative spatial computing that explicitly combines both location and social factors to answer useful geo-social queries for either business or social good. In this paper, we study a new type of Geo-Social K-Cover Group (GSKCG) queries that, given a set of query points and a social network, retrieves a minimum user group in which each user is socially related to at least $k$ other users and the users’ associated regions (e.g., familiar regions or service regions) can jointly cover all the query points. Albeit its practical usefulness, the GSKCG query problem is NP-complete. We consequently explore a set of effective pruning strategies to derive an efficient algorithm for finding the optimal solution. Moreover, we design a novel index structure tailored to our problem to further accelerate query processing. Extensive experiments demonstrate that our algorithm achieves desirable performance on real-life datasets.

POI Pulse: A Multi-granular, Semantic Signature–Based Information Observatory for the Interactive Visualization of Big Geosocial Data

The volume, velocity, and variety of data that are now becoming available allow us to study urban environments based on human behaviour with a spatial, temporal, and thematic granularity that was not achievable until now. Such data-driven approaches open up additional, complementary perspectives on how urban systems function, especially if they are based on user-generated content (UGC). While the data sources, such as social media, introduce specific biases, they also open up new possibilities for scientists and the broader public. For instance, they provide answers to questions that previously could only be addressed by complex simulations or extensive human-participant surveys. Unfortunately, many of the required data sets are locked in data silos that are accessible only via restricted APIs. Even if these data could be fully accessed, their naïve processing and visualization would surpass the abilities of modern computer architectures. Finally, the established place schemata used to study urban spaces differ substantially from UGC-based point-of-interest (POI) schemata. In this work, we present a multi-granular, data-driven, and theory-informed approach that addresses the key issues outlined above by introducing a theoretical and technical framework to interactively explore the pulse of a city based on social media.

Object Selection in Map Generalization Using Geosocial Network Data: A Case Study in Wuhan, China

In map generalization, determining which objects are to be selected is a challenging task in the selection operation. Decisions surrounding object selection depend on object semantics and spatial context. The advent of geosocial network services, such as Foursquare and Twitter, provides an evaluation system for physical space. These services have generated a wealth of geographic information that can reflect human mobility and urban dynamics. The purpose of this paper is to use the geographic information from geosocial networks as a reference for map generalization and subsequently transform the semantic-based selection operator into a simple statistical method. Analysing this geographic information quantitatively and acquiring the value of each object is the key of this research. The present study has organized an investigation using data from a geosocial network service, named Jiepang in Wuhan, China. The experiment was conducted by adopting spatial analysis and heavy-tailed distribution, which consisted of the following steps: first, semi-variance modelling was conducted for the distance threshold, to measure the magnitude of the effect of spatial dependence; a buffer analysis was then completed using a radius of this distance threshold and inverse distance weighting was applied to calculate the value of the geographic object; last, a head/tail division rule, a new principle based on heavy-tailed distribution, was used to select objects at different levels of detail. Though it is difficult to evaluate map generalization, the result demonstrates a different map. Furthermore, for a better understanding of the result, the method used in this study is compared to OpenStreetMap and essential differences between the two are discussed. This study successfully demonstrates that geosocial network data can be used as important criteria for object selection.

Measure of Landmark Semantic Salience through Geosocial Data Streams

Research in the area of spatial cognition demonstrated that references to landmarks are essential in the communication and the interpretation of wayfinding instructions for human being. In order to detect landmarks, a model for the assessment of their salience has been previously developed by Raubal and Winter. According to their model, landmark salience is divided into three categories: visual, structural, and semantic. Several solutions have been proposed to automatically detect landmarks on the basis of these categories. Due to a lack of relevant data, semantic salience has been frequently reduced to objects’ historical and cultural significance. Social dimension (i.e., the way an object is practiced and recognized by a person or a group of people) is systematically excluded from the measure of landmark semantic salience even though it represents an important component. Since the advent of mobile Internet and smartphones, the production of geolocated content from social web platforms—also described as geosocial data—became commonplace. Actually, these data allow us to have a better understanding of the local geographic knowledge. Therefore, we argue that geosocial data, especially Social Location Sharing datasets, represent a reliable source of information to precisely measure landmark semantic salience in urban area.

Partner-marketing using geo-social media data for smarter commerce

As a result of significantly growing competition from online-only retailers, physical store retailers have resorted to measures such as discount coupons, online price matching, sale events, and a seamless omnichannel customer experience. One important, often overlooked method is <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">partner-marketing</i> , where a retailer promotes products or services offered by other merchants. The main challenge in partner-marketing is finding partners, i.e., determining whom a retailer should choose as partners among many choices. In this paper, we discuss how a retailer can make use of rich information from mobile and geo-social media to find potential partners in a geographic region. The explosion of mobile and geo-social media in recent years has led to increasing insights about consumers' footprints—which shops they visit, where they travel, and where they live and work. In addition, geo-social data also reveals which regional merchants are popular and why. We propose a series of partner-finding techniques that leverage geo-social data at increasing granularity and discuss analytics to rank potential partners. We present compelling business case studies using real data from Foursquare, a social networking website. We also discuss how retailers can combine geo-social data with traditional data such as demographics, weather information, and their own marketing databases to personalize partner-marketing.

Digital Narratives: Mapping Contemporary Use of Urban Open Spaces through Geo-social Data

Over the last decade, new spatial means have been keenly developed on geo-social, location-based networking systems and more recently through mobile applications, with significant personalized digital content, full of cognitive and perceptive clues. Culling this information and having it as the main source of analysis, this study explores the cartography of the city of Rio de Janeiro, portraying some of its outdoors recreational activities that are partially invisible in the daily life, advocating the potentiality of this methodological and theoretical framework to disrupt traditional spatial paradigms and contributes to urban research, design, education and representation.

Spatial modelling of road network development, population pressure and biophysical properties of upland crop and forest conversions in Lop Buri province, Thailand, 1989–2006

Over the past few decades, land use and land cover change has become a global concern. In the Lop Buri province of Thailand, rapid land cover change, specifically conversion of forests to agriculture, has occurred. The purpose of the study is to identify the predictors of land cover change in Lop Buri province for land that has been converted to upland crops or has undergone deforestation between 1989 and 2006. Four logistic regression models were constructed using spatially explicit biophysical and geo‐social data, to account for changes to upland crops and forest loss from1989–98 and 1998–2006. Across the four models, slope, distance to forest edge, distance to towns, distance to roads, population size, and population density in various stand‐alone and interactive forms were found to be the most consistent predictors of land cover change.

The emergent urban imaginaries of geosocial media

A class of geosocial software applications has begun to emerge that integrates location and social networking. These applications enable public participation in the production of datasets that reveal patterns of individual perception, interaction, and experience in space. Geosocial data consist of point locations that have been created and tagged by participants with short statements about their perceptions and/or experiences. Increasingly, these data are streamed via map interface by ‘meta-geosocial’ aggregation services and are freely available to the public. In this article I suggest that as geosocial applications become more popular, the composite sketches of place that result from them will constitute increasingly accurate representations of the local collective socio-spatial imaginary. Using data collected from one of the more popular geosocial media services, I explore the proposition that collective digital imaginaries have the potential to emerge from geosocial data. And drawing on the literature of the imaginary, I argue that geosocial-based imaginaries do not simply reflect socio-spatial practice, but also inform and influence the ways that we perceive, experience and interact in space.