Location-based Social Media Research Articles

A Novel Methodology to Label Urban Remote Sensing Images Based on Location-Based Social Media Photos

With the rapid development of the internet and popularization of intelligent mobile devices, social media is evolving fast and contains rich spatial information, such as geolocated posts, tweets, photos, video, and audio. Those location-based social media data have offered new opportunities for hazards and disaster identification or tracking, recommendations for locations, friends or tags, pay-per-click advertising, etc. Meanwhile, a massive amount of remote sensing (RS) data can be easily acquired in both high temporal and spatial resolution with a multiple satellite system, if RS maps can be provided, to possibly enable the monitoring of our location-based living environments with some devices like charge-coupled device (CCD) cameras but on a much larger scale. To generate the classification maps, usually, labeled RS image pixels should be provided by RS experts to train a classification system. Traditionally, labeled samples are obtained according to ground surveys, image photo interpretation or a combination of the aforementioned strategies. All the strategies should be taken care of by domain experts, in a means which is costly, time consuming, and sometimes of a low quality due to reasons such as photo interpretation based on RS images only. These practices and constraints make it more challenging to classify land-cover RS images using big RS data. In this paper, a new methodology is proposed to classify urban RS images by exploiting the semantics of location-based social media photos (SMPs). To validate the effectiveness of this methodology, an automatic classification system is developed based on RS images as well as SMPs via big data analysis techniques including active learning, crowdsourcing, shallow machine learning, and deep learning. As the labels of RS training data are given by ordinary people with a crowdsourcing technique, the developed system is named Crowd4RS. The quantitative and qualitative experiments confirm the effectiveness of the proposed Crowd4RS system as well as the proposed methodology for automatically generating RS image maps in terms of classification results based on big RS data made up of multispectral RS images in a high spatial resolution and a large amount of photos from social media sites, such as Flickr and Panoramio.

Quantifying and visualizing language diversity of Hong Kong using Twitter

The wide penetration of location-aware mobile devices and location-based services renders the location-based social media as a reliable proxy to study the real-world geographic space. Language diversity is an important indicator of a city's internationalization level. People communicate using different languages in the cyberspace of social media as they do in the geographic space. The location-based social media therefore provides an innovative set of lens to map the language diversity and study the internationalization of cities. In the enclosed graphics, based on a collection of geo-tagged Twitter posts, we generated a fine resolution map of language diversity index in the area of Hong Kong to illustrate the potential of location-based social media in city research.

Ranking the City: The Role of Location-Based Social Media Check-Ins in Collective Human Mobility Prediction

Technological advances have led to an increasing development of data sources. Since the introduction of social networks, numerous studies on the relationships between users and their behaviors have been conducted. In this context, trip behavior is an interesting topic that can be explored via Location-Based Social Networks (LBSN). Due to the wide availability of various spatial data sources, the long-standing field of collective human mobility prediction has been revived and new models have been introduced. Recently, a parameterized model of predicting human mobility in cities, known as rank-based model, has been introduced. The model predicts the flow from an origin toward a destination using “rank” concept. However, the notion of rank has not yet been well explored. In this study, we investigate the potential of LBSN data alongside the rank concept in predicting human mobility patterns in Manhattan, New York City. For this purpose, we propose three scenarios, including: rank-distance, the number of venues between origin and destination, and a check-in weighted venue schema to compute the ranks. When trip distribution patterns are considered as a whole, applying a check-in weighting schema results in patterns that are approximately 10 percent more similar to the ground truth data. From the accuracy perspective, as the predicted numbers of trips are closer to real number of trips, the trip distribution is also enhanced by about 50 percent.

Enhancing Location-Based Social Media Network Services with Semantic Technologies: A Review

Today’s location-based social media services have gone beyond mere sharing users’real-time locationsvia internet, they now serve as the bridge between the real world and the online world. Location-based social media application can now recommend point of interest to users based on geographical information and user’s profile gatheredon social media networks. Semantic web technology provides tools,platforms and techniques to extract meaning, processand integrate structure datafrom the social web and other sources.The rapid increasein number of social media networks and theenormous amount of geographical and social data flow across mobile and web platforms, have not only provided rich data source for web applications but also help developers to facilitate location-based social media services. However, unprecedented amount of noise and unstructured data exist on these networks, making knowledge representation, point of interest recommendation and precision of search engine results cumbersome processes.In this paper, we presentreview of various semantic technologies that could bedeployed to enhance location-based social media services with emphasis on architectures, tools, supporting technologies and the pros and cons of each of these technologies.

Using locative social media and urban cartographies to identify and locate successful urban plazas

Locative social media networks as open sources of data allow researchers and professionals to acknowledge which city places are preferred, used and livable. Following this hypothesis, this paper proposes a methodology to identify successful public spaces – plazas – through the location-based social media network Foursquare and to analyze their urban position using morphological and historical cartographies.The overall methodology comprises three stages. First, the most important cities of the province of Alicante were selected. Second, the most relevant plaza of each city was identified using data retrieved from the social network Foursquare. Finally, the location of each plaza is analyzed in relation to the historic center and the main axes of the city. Possible correlations between their urban location and their vibrant character were subsequently identified.Two findings have emerged from this study: (a) a strong spatial relationship exists between the most successful plazas and the historic city center, which reinforces their traditional social character; and (b) all plazas share two similar traits, their location within the urban network and their proximity to the main axes of the city.

A Socio‐Geographic Perspective on Human Activities in Social Media

Location‐based social media make it possible to understand social and geographic aspects of human activities. However, previous studies have mostly examined these two aspects separately without looking at how they are linked. The study aims to connect two aspects by investigating whether there is any correlation between social connections and users' check‐in locations from a socio‐geographic perspective. We constructed three types of networks: a people–people network, a location–location network, and a city–city network from former location‐based social media Brightkite and Gowalla in the U.S., based on users' check‐in locations and their friendships. We adopted some complexity science methods such as power‐law detection and head/tail breaks classification method for analysis and visualization. Head/tail breaks recursively partitions data into a few large things in the head and many small things in the tail. By analyzing check‐in locations, we found that users' check‐in patterns are heterogeneous at both the individual and collective levels. We also discovered that users' first or most frequent check‐in locations can be the representatives of users' spatial information. The constructed networks based on these locations are very heterogeneous, as indicated by the high ht‐index. Most importantly, the node degree of the networks correlates highly with the population at locations (mostly with R2 being 0.7) or cities (above 0.9). This correlation indicates that the geographic distributions of the social media users relate highly to their online social connections.

Visualizing the gay community in Beijing with location-based social media

Visualizing the gay community in Beijing with location-based social media

Processing uncertain spatial data resulting from differentially-private sanitization

The unprecedented revolution in mobile computing provides users with the ability to participate in applications that are customized to their spatial coordinates. Location-based social media and location-based recommendations are only two examples of popular scenarios where the use of geographical location can significantly improve user experience. However, serious privacy concerns arise when sharing users' locations, as an adversary may be able to derive sensitive personal details from one's whereabouts, such as health status, political or religious orientation, alternative lifestyles, etc. Privacy models such as differential privacy (DP) are commonly employed to protect individuals' whereabouts before sharing. Typically, privacy is achieved by introducing uncertainty with respect to a user's location. In this setting, uncertain data processing techniques become a natural choice for processing user location data that have been previously sanitized to protect privacy. In this article, we discuss some prominent scenarios where it is important to protect location data, and we explain how the de-facto standard of differentially-private location protection can be used in conjunction with uncertain data processing. We also look at a highly promising use case scenario of interest, namely privacy-preserving spatial crowd-sourcing, and provide an overview of how DP and uncertain data processing are combined to address this problem.

Putting people in the picture: Combining big location-based social media data and remote sensing imagery for enhanced contextual urban information in Shanghai

Urbanization is a set of interrelated processes; the most visible among them are changes in the built-up environment. We relate those changes to human activity as expressed by online social media messages. This approach might shed light on urban dynamics currently intractable through existing datasets and methodologies. Microwave remote sensing images are used to identify urban built-up areas and changes within those areas in an objective way, while geocoded mobile social media messages deliver valuable information about human activity and the vitality found in those areas. A time-series stack of 36 TerraSAR-X Stripmap images and roughly six million social media messages were processed, classified, and visually and quantitatively analyzed for an experiment in Shanghai. We derived four possible cases of land classification by combining the results of both sources to a single raster layer at a 400m cell size. Quantifying these cases in a 2-by-2 confusion matrix shows positive and negative matches between built-up areas and social media messages. We see that correlation of positive matches is 72%. A combination of remotely sensed and social media data is a step towards a more granular analysis of urbanization processes than is possible from either data source alone. We put people in the picture of traditional remote sensing analysis.

Using Location-Based Social Media to Chart the Patterns of People Moving between Cities: The Case of Weibo-Users in the Yangtze River Delta

Urban-geographical research using location-based social media (LBSM) has itself been characterized by uneven geographies in that most studies deal with Europe and North America. This implies a relative dearth of studies focusing on countries such as China, and this in spite of the country having the largest number of Internet users in the world. This paper proposes to address this lacuna by showing the research potential of LBSM services associated with Weibo, by far the most popular online social microblogging and networking service in China. To this end, we map inter-city connections within the Yangtze River Delta based on three million individuals’ space-time footprints derived from Weibo. Empirical results reveal that the inter-city connections derived from Weibo present both common and specific spatial patterns associated with inter-city travel. We find that a small percentage of cities and city-dyads constitute the backbone of this inter-city network. The dominant direction of individual flows tends to be from primary cities to sub-primary cities, and from peripheral cities to primary cities. In addition, city-dyad connectivities do not strictly follow cities’ positions in terms of their centralities in the hierarchical distribution. Furthermore, the effects of administrative boundaries and cities’ administrative level are significant. We benchmark these insights by re-examining our findings against the backdrop of polycentric developments in the Yangtze River Delta, which confirms the potential usefulness of LBSM data for analyzing urban-geographical patterns.

Jumping for Fun? Negotiating Mobility and the Geopolitics of Foursquare

Rather than assume that there is some universal “right way” to engage social media platforms, we interrogate how the location-based social media practice known as “jumping” played out on the popular service Foursquare. We use this case to investigate how a “global” or universal system is constructed with an imagined user in mind, one who enjoys a particular type of mobility and experience of place. Through the analysis of official Foursquare policies and mission statements, discussions among developers, interviews with and conversations among Foursquare users, online traces left by jumpers, and correspondence between designers and users on discussion forums, we identify how certain practices and participants are discursively constructed as normative, while other practices and groups are marginalized. Through the study of “jumping,” and its association with Indonesian players in particular, we highlight tensions between the assumptions and industrial strategies of Foursquare designers and the emergent practices and norms of early adopters and avid participants. We argue that the practices of “Indonesian” Foursquare jumpers and the discourses surrounding their use of Foursquare illustrate that practices understood as transgressive or resistive might best be read as strategies for engaging with a platform as groups contend with marginalizing social, economic, and/or political conditions. The case study examined in this article highlights the practices of participants who attempt to integrate themselves into the design of a social media system and the “workarounds,” tensions, negotiations, and logics that manifest in that process.

Where Is Portland Made? The Complex Relationship between Social Media and Place in the Artisan Economy of Portland, Oregon (USA)

Where Is Portland Made? The Complex Relationship between Social Media and Place in the Artisan Economy of Portland, Oregon (USA)

We Know Where You Are

The convergence of social media and GIS provides an opportunity to reconcile space-based GIS and place-based social media. For this purpose, the authors conduct an empirical study in Columbus, Ohio, aiming to enrich both the spatial and platial context of geo-tagged data, using location-based social media Foursquare checkins as an example. An exploratory analytical approached is used to enrich the geographic context of social media data in both space and place. Specifically, exploratory spatial data analysis and point of interest matching are applied to analyze about 50,000 checkins crawled from social media feeds. It is found that checkins tend to be spatially clustered near the center of the city. Popular places related to food, services, and retail shopping venues are more likely to be reported by social media users. The authors also conducted platial analysis of the top 25 popular place venues in the study area.

STCAPLRS

Newly emerging location-based social media network services (LBSMNS) provide valuable resources to understand users’ behaviors based on their location histories. The location-based behaviors of a user are generally influenced by both user intrinsic interest and the location preference, and moreover are spatial-temporal context dependent. In this article, we propose a spatial-temporal context-aware personalized location recommendation system (STCAPLRS), which offers a particular user a set of location items such as points of interest or venues (e.g., restaurants and shopping malls) within a geospatial range by considering personal interest, local preference, and spatial-temporal context influence. STCAPLRS can make accurate recommendation and facilitate people’s local visiting and new location exploration by exploiting the context information of user behavior, associations between users and location items, and the location and content information of location items. Specifically, STCAPLRS consists of two components: offline modeling and online recommendation. The core module of the offline modeling part is a context-aware regression mixture model that is designed to model the location-based user behaviors in LBSMNS to learn the interest of each individual user, the local preference of each individual location, and the context-aware influence factors. The online recommendation part takes a querying user along with the corresponding querying spatial-temporal context as input and automatically combines the learned interest of the querying user, the local preference of the querying location, and the context-aware influence factor to produce the top- k recommendations. We evaluate the performance of STCAPLRS on two real-world datasets: Dianping and Foursquare. The results demonstrate the superiority of STCAPLRS in recommending location items for users in terms of both effectiveness and efficiency. Moreover, the experimental analysis results also illustrate the excellent interpretability of STCAPLRS.

Explore spatiotemporal and demographic characteristics of human mobility via Twitter: A case study of Chicago

Characterizing human mobility patterns is essential for understanding human behaviors and the interactions with socioeconomic and natural environment, and plays a critical role in public health, urban planning, transportation engineering and related fields. With the widespread of location-aware mobile devices and continuing advancement of Web 2.0 technologies, location-based social media (LBSM) have been gaining widespread popularity in the past few years. With an access to locations of hundreds of million users, profiles and the contents of the social media posts, the LBSM data provided a novel modality of data source for human mobility study. By exploiting the explicit location footprints and mining the latent demographic information implied in the LBSM data, the purpose of this paper is to investigate the spatiotemporal characteristics of human mobility with a particular focus on the impact of demography. To serve this purpose, we first collect geo-tagged Twitter feeds posted in the conterminous United States area, and organize the collection of feeds using the concept of space-time trajectory corresponding to each Twitter user. Commonly human mobility measures, including detected home and activity centers, are derived for each user trajectory. We then select a subset of Twitter users that have detected home locations in the city of Chicago as a case study, and apply name analysis to the names provided in user profiles to learn the implicit demographic information of Twitter users, including race/ethnicity, gender and age. Finally we explore the spatiotemporal distribution and mobility characteristics of Chicago Twitter users, and investigate the demographic impact by comparing the differences across three demographic dimensions (race/ethnicity, gender and age). We found that, although the human mobility measures of different demographic groups generally follow the generic laws (e.g., power law distribution), the demographic information, particular the race/ethnicity group, significantly affects the urban human mobility patterns.

Microsummarization of Online Reviews: An Experimental Study

Mobile and location-based social media applications provide platforms for users to share brief opinions about products, venues, and services. These quickly typed opinions, or microreviews, are a valuable source of current sentiment on a wide variety of subjects. However, there is currently little research on how to mine this information to present it back to users in easily consumable way. In this paper, we introduce the task of microsummarization, which combines sentiment analysis, summarization, and entity recognition in order to surface key content to users. We explore unsupervised and supervised methods for this task, and find we can reliably extract relevant entities and the sentiment targeted towards them using crowdsourced labels as supervision. In an end-to-end evaluation, we find our best-performing system is vastly preferred by judges over a traditional extractive summarization approach. This work motivates an entirely new approach to summarization, incorporating both sentiment analysis and item extraction for modernized, at-a-glance presentation of public opinion.

Predicting adoption of location-based social media service in travel decisions

Advances in location-acquisition and mobile communication technologies have empowered people to use location-based social media. However, the technologies are relatively new, and there is little literature on the relevant factors determining location-based social media adoption. We examine if the online information reviews information can predict users' location-based social media usage for travel planning. The results of this study will be useful for location-based social media providers in formulating appropriate marketing strategies and in developing applications that will attract more users.

AP-Tree: efficiently support location-aware Publish/Subscribe

We investigate the problem of efficiently supporting location-aware Publish/Subscribe (Pub/Sub for short), which is essential in many applications such as location-based recommendation and advertising, thanks to the proliferation of geo-equipped devices and the ensuing location-based social media applications. In a location-aware Pub/Sub system (e.g., an e-coupon system), subscribers can register their interest as spatial-keyword subscriptions (e.g., interest in nearby iphone discount); each incoming geo-textual message (e.g., geo-tagged e-coupon) will be delivered to all the relevant subscribers immediately. While there are several prior approaches aiming at providing efficient processing techniques for this problem, their approaches belong to spatial-prioritized indexing method which cannot well exploit the keyword distribution. In addition, their textual filtering techniques are built upon simple variants of traditional inverted indexes, which do not perform well for the textual constraint imposed by the problem. In this paper, we address the above limitations and provide a highly efficient solution based on a novel adaptive index, named AP-Tree. AP-Tree adaptively groups registered subscriptions using keyword and spatial partitions, guided by a cost model. AP-Tree also naturally indexes ordered keyword combinations. Furthermore, we show that our techniques can be extended to process moving spatial-keyword subscriptions, where subscribers can continuously update their locations. We present efficient algorithms to process both stationary and moving subscriptions, which can seamlessly and effectively integrate keyword and spatial partitions. Our extensive experiments demonstrate that AP-Tree and its variant AP $$^{+}$$+ -Tree can achieve up to an order of magnitude improvement on efficiency compared with prior state-of-the-art methods.

Effect of climate and seasonality on depressed mood among twitter users

Location-based social media provide an enormous stream of data about humans' life and behavior. With geospatial methods, those data can offer rich insights into public health. In this research, we study the effect of climate and seasonality on the prevalence of depression in Twitter users in the U.S. Text mining and geospatial methods are used to detect tweets related to depression and their spatiotemporal patterns at the scale of Metropolitan Statistical Area. We find the relationship between depression rates, climate risk factors and seasonality are varied and geographically localized. The same climate measure may have opposite association with depression rates at different places. Relative humidity, temperature, sea level pressure, precipitation, snowfall, weed speed, globe solar radiation, and length of day all contribute to the geographic variations of depression rates. A conceptual compact map is designed to visualize scattered geographic phenomena in a large area. We also propose a three-stage framework that semi-automatically detects and analyzes geographically distributed health issues using location-based social media data.

위치기반 소셜 미디어 데이터의 텍스트 마이닝 기반 공간적 클러스터링 분석 연구

위치기반 소셜 미디어 데이터는 빅데이터, 위치기반서비스 등 다양한 분야에서 활용가능성이 매우 큰 데이터이다. 본 연구에서는 위치기반 소셜 미디어 데이터의 텍스트 정보를 분석하여 주요한 키워드들이 공간적으로 어떻게 분포하고 있는지를 파악할 수 있는 일련의 분석방법론을 적용해보았다. 이를 위해, 위치태그를 지닌 트윗 데이터를 서울시 강남지역과 그 주변지역에 대하여 2013년 8월 한달 간 수집하였으며, 이 데이터를 대상으로 하여 텍스트 마이닝을 통해 주요 키워드들을 도출하였다. 이러한 키워드들 중 음식, 엔터테인먼트, 업무 및 공부의 세 카테고리에 해당하는 키워드들만 추출, 분류하였으며 각 카테고리에 해당하는 트윗 데이터들에 대해서 공간적 클러스터링을 실시하였다. 도출된 각 카테고리별 클러스터들을 실제 그 지역의 건물 또는 벤치마크 POI들과 비교한 결과, 음식 카테고리 클러스터는 대규모 상업지역들과 일치도가 높았고 엔터테인먼트 카테고리의 클러스터는 공연장, 극장, 잠실운동장 등과 일치하였다. 업무 및 공부 카테고리 클러스터들은 학원 밀집지역 및 사무용 빌딩 밀집지역과 높은 일치도를 나타내었다.