Search results

The purpose of this paper is to clarify the correlations between amount of individual’s knowledge of a specific area and his/her visit pattern to point of interest (POI, interested places) located in the area.

This paper proposes a visit-frequency-based familiarity estimation method that estimates individuals’ knowledge of areas in a quantitative manner. Based on the familiarity degree, individuals’ visit logs to POIs are divided into a set of groups followed by analyzing the differences among the groups from various points of view, such as user preference, POI categories/popularity, visit time/date and subsequent visits.

Existence of statistically significant correlations between individuals’ familiarity to areas and their visit patterns is observed by our analysis using 1.4-million POI visit logs collected from a popular location-based social network (LBSN), Foursquare. There exist different skewness of the visit time and visited POI distribution/popularity with regard to the familiarity. For instance, users go to unfamiliar areas on weekends and visit POIs for cultural experiences, such as museums. A notable point is that the correlations can be detected even in the areas in home city, which have not been known so far.

This is the first in-depth work that studies both estimation of individuals’ familiarity and correlations between the familiarity and individuals’ mobility patterns by analyzing massive LBSN data. The methodologies used and the findings of this work can be applicable not only to human mobility analysis for sociology, but also to POI recommendation system design.

This chapter is concerned with examining the families that play Pokémon Go together within the context of spatial practices. The chapter begins by outlining the general approach to spatiality that we adopt throughout this book, which is predicated on the ‘spatial turn’ within the social sciences. Here, spatial practices are understood as being socially constructed in day-to-day live, as opposed to being something simply given. In other words, ‘the concept of the city’ and the ‘urban fact’ (de Certeau, 1984, p. 1, italics in original) are not one and the same thing. Instead, the phenomenology of space is moulded in the social realm as part of the practice of everyday life, which has consequences for hybrid reality games (HRGs) like Pokémon Go. After delineating between ‘space’ and ‘place’ à la the ‘mobilities turn’, we shift our attention to embodied approaches to urban life. This begin with an examination of the art of the flânerie, which has been reimagined to account for the ubiquity of mobile media, and more recently, locative games. A review of the literature surrounding locative games demonstrates that, for the most part, concerns about spatiality have not extended to the kind of intergenerational play that is the focus of this book. Drawing on our original study of Pokémon Go, as outlined above, then, the chapter is driven by the following research questions. First, to what extent does Pokémon Go lead to families spending more time outside and how is this reshaping experienced. Second, what effect does this HRG has on the routes and pathways families choose to follow while traversing their physical setting, as well as the sites they frequent. Third, to what extent do families engage with the various elements of Pokémon Go and what does this suggest about the evolution of locative play in the context of earlier location-based social networks (LBSNs).

Tourism spot or point-of-interest (POI) recommendation has become a common service in people's daily life. The purpose of this paper is to model users' check-in history in order to predict a set of locations that a user may soon visit.

The authors proposed a novel learning-based method, the pattern-based dual learning POI recommendation system as a solution to consider users' interests and the uniformity of popular POI patterns when making recommendations. Differing from traditional long short-term memory (LSTM), a new users’ regularity–POIs’ popularity patterns long short-term memory (UP-LSTM) model was developed to concurrently combine the behaviors of a specific user and common users.

The authors introduced the concept of dual learning for POI recommendation. Several performance evaluations were conducted on real-life mobility data sets to demonstrate the effectiveness and practicability of POI recommendations. The metrics such as hit rate, precision, recall and F-measure were used to measure the capability of ranking and precise prediction of the proposed model over all baselines. The experimental results indicated that the proposed UP-LSTM model consistently outperformed the state-of-the-art models in all metrics by a large margin.

This study contributes to the existing literature by incorporating a novel pattern–based technique to analyze how the popularity of POIs affects the next move of a particular user. Also, the authors have proposed an effective fusing scheme to boost the prediction performance in the proposed UP-LSTM model. The experimental results and discussions indicate that the combination of the user's regularity and the POIs’ popularity patterns in PDLRec could significantly enhance the performance of POI recommendation.

The purpose of this paper is to explore how narrative discourses frames entrepreneurial knowledge – in the form of understandings and meanings – focusing the role of business support in stimulating black entrepreneurship. It reveals the assumptions and values associated with business support from the point of view of the providers – who themselves are categorized as “black”.

A collaborative narrative approach is adopted to locate knowledge of business support within the “life‐world” of black business support providers. The research was conducted at two levels: focus group and narrative interviews.

The paper highlights the ways in which dominant discourses guide as well as constrain the representation of black businesses. Low take‐up of business support is contested. Public‐funded business support programmes are perceived as unwholesome, unwieldy and inherently inadequate in meeting the strategic development needs of black businesses.

Focusing on actual engagement rather than content aspects of the business support policy framework reveals a need for more dialogic research to explore more deeply whether, and to what extent, alternative and new perspectives on supporting black businesses are needed.

The novelty of this paper lies in attempting to unravel the complex processes of business support provision in the context of black entrepreneurship by decoding the narrative discourses used by support providers who are themselves categorized as “black”. Such intrinsic examination of views and beliefs is relatively unique and provides an interesting platform for further research.

Projecting the population distribution in geographical regions is important for many applications such as launching marketing campaigns or enhancing the public safety in certain densely populated areas. Conventional studies require the collection of people’s trajectory data through offline means, which is limited in terms of cost and data availability. The wide use of online social network (OSN) apps over smartphones has provided the opportunities of devising a lightweight approach of conducting the study using the online data of smartphone apps. This paper aims to reveal the relationship between the online social networks and the offline communities, as well as to project the population distribution by modeling geo-homophily in the online social networks.

In this paper, the authors propose the concept of geo-homophily in OSNs to determine how much the data of an OSN can help project the population distribution in a given division of geographical regions. Specifically, the authors establish a three-layered theoretic framework that first maps the online message diffusion among friends in the OSN to the offline population distribution over a given division of regions via a Dirichlet process and then projects the floating population across the regions.

By experiments over large-scale OSN data sets, the authors show that the proposed prediction models have a high prediction accuracy in characterizing the process of how the population distribution forms and how the floating population changes over time.

This paper tries to project population distribution by modeling geo-homophily in OSNs.

Recent smart mobile devices are capable of letting users produce various digital content, and share/upload the content to many social network services (SNS) directly via wireless network connections. The phenomenon has increased the number of people using mobile SNS applications. Although the applications have become more popular, mobile users have been restricted in the virtual communities of online SNS and are not aware of the social opportunities available to them in real-time surrounding. While they spend most of their time accessing online SNS, they have missed many opportunities to interact with others for new friendships, business opportunities or information sharing. Consequently, a new breed of mobile social network (MSN) system has arisen to assist mobile users to interact with proximal people and perform various social activities. Such a proximal-based MSN environment is termed a Mobile Social Network in Proximity (MSNP).

Developing an MSNP system needs to address a number of issues and challenges, such as heterogeneity, content/service discovery, privacy and trust, resource management, and so on. This paper identifies and describes these challenges, and reviews a number of related solutions from existing literature. In the follow up, this paper addresses a number of open challenges in the MSNP domain.

Although various works have been proposed to enable and overcome challenges in MSNP, there are still many unsolved open challenges in terms of identification, content management, social-aware discovery, trust in public environment, adaptation, quality of service and the development of MSNP. We have addressed these challenges in this paper as future research directions in the MSNP domain.

This paper provides an original literature review in MSNP and identifies a number of open challenges as research direction in the MSNP domain.

This chapter reiterates the conclusions drawn on Pokémon Go in the context of intergenerational play. We begin by reflecting on the exigency of this book, before summarising our key findings under the following headings: (1) spatial activity and cognisance, (2) familial rhythms and digital labour, (3) playful bonding and ‘non-confrontational spaces’, (4) personal development and cursory connections, (5) familial challenges and concerns, (6) surveillance and the game beneath the game. Importantly, these findings are discussed in a manner that extends beyond the specificity of Pokémon Go. That is to say, our findings are used to establish how the next generation of locative games differs from the previous generations. Here, we pay particular attention to the various ways this current generation is predicated on a more dynamic digital architecture than earlier locative games and location-based social networks (LBSNs). Accordingly, this section is critical in terms of both surveying the area as it stands and positioning the current project in the canon of both locative media and intergenerational play. Moving forward, we reflect on how the experience of playing Pokémon Go has changed to accommodate the social restrictions put in place to help combat the COVID-19 global pandemic (Byford, 2020a, 2020b; Orland, 2020; Takahashi, 2020). In particular, this section highlights the adaptability of current hybrid reality games (HRGs) such as Pokémon Go in the wider field of locative games. Finally, this section looks to the future by deliberating how Pokémon Go might continue to develop in a COVID-19 world and what these developments might suggest about our approach to environments that increasingly feel at odds with the notion of play.

This paper aims to address the following issues: (1) most existing methods are based on recurrent network, which is time-consuming to train long sequences due to not allowing for full parallelism; (2) personalized preference generally are not considered reasonably; (3) existing methods rarely systematically studied how to efficiently utilize various auxiliary information (e.g. user ID and time stamp) in trajectory data and the spatiotemporal relations among nonconsecutive locations.

The authors propose a novel self-attention network–based model named SanMove to predict the next location via capturing the long- and short-term mobility patterns of users. Specifically, SanMove uses a self-attention module to capture each user's long-term preference, which can represent her personalized location preference. Meanwhile, the authors use a spatial-temporal guided noninvasive self-attention (STNOVA) module to exploit auxiliary information in the trajectory data to learn the user's short-term preference.

The authors evaluate SanMove on two real-world datasets. The experimental results demonstrate that SanMove is not only faster than the state-of-the-art recurrent neural network (RNN) based predict model but also outperforms the baselines for next location prediction.

The authors propose a self-attention-based sequential model named SanMove to predict the user's trajectory, which comprised long-term and short-term preference learning modules. SanMove allows full parallel processing of trajectories to improve processing efficiency. They propose an STNOVA module to capture the sequential transitions of current trajectories. Moreover, the self-attention module is used to process historical trajectory sequences in order to capture the personalized location preference of each user. The authors conduct extensive experiments on two check-in datasets. The experimental results demonstrate that the model has a fast training speed and excellent performance compared with the existing RNN-based methods for next location prediction.