Discovery of spatio-temporal patterns from location-based social networks

Béjar, Javier; Álvarez, S.; García, David; Gomez, Ignacio; Oliva, Luis; Tejeda, A.L.; Vázquez-Salceda, Javier

doi:10.1080/0952813x.2015.1024492

Cited by 17 publications

(14 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Moreover, the spatial distribution of our research also coincides with the pattern of tourist distribution in some other cities, as described in the literature review. This result is similar to the conclusion of Béjar et al (2014) which utilizes Instagram data, a finding that indicates different datasets may be comparable, as long as the volume of the dataset is substantial.…”

Section: Discussionsupporting

confidence: 83%

“…Hasnat et al (2018) described tourist movements as clustered around tourist attractions based on Twitter data in Florida. Béjar et al (2014) extracted the spatial-temporal characteristics of Twitter and Instagram users in Barcelona; they found that the main tourist attractions were important connecting nodes in both datasets, though their study did not distinguish tourist users from locals. Kádár (2014) concluded that the majority of geo-tagged images generated from Flickr tourist users were gathered around tourist attractions or landmarks in Budapest.…”

Section: Study Of Tourist Activities Based On Lbsn Datamentioning

confidence: 99%

See 1 more Smart Citation

Identifying tourist-functional relations of urban places through Foursquare from Barcelona

Yang

Durarte

2019

GeoJournal

View full text Add to dashboard Cite

Previous research has mainly focused on spatial relations among tourist attractions in urban areas. However, few studies have examined the functional relations between tourist attractions and other urban places (i.e. the flows of tourists between them). Therefore, this study focuses on quantification of the tourist-functional relations among Places of Interest (POIs) using Foursquare data from Barcelona. This represents an effort to highlight the important functional closeness between different types of POIs whose significance is not usually obvious from their spatial relationships. In order to quantify these functional relationships, this paper classifies Foursquare POIs into 22 categories according to their different usages and constructs a matrix of usage-flows to depict the connections among these different usages. A model of interaction values is introduced to describe the strength of relations and identify the dominant tourist usages. The results confirm that the functional centroids differ from these spatial distributions which only focused around tourist attractions. In addition to tourist attractions, places in the categories of Restaurants, Transport, and Hotels play important roles in functional relationship of tourism. The typical urban usages of tourists can be distinguished by the interaction values between these categories. Our model provides a practical method to quantify the interlinkage of usages of POIs based on tourist flows. In particular, LBSN data has potential as a method to observe the tourist-functional relations among places.

show abstract

Section: Discussionsupporting

confidence: 83%

Section: Study Of Tourist Activities Based On Lbsn Datamentioning

confidence: 99%

Identifying tourist-functional relations of urban places through Foursquare from Barcelona

Yang

Durarte

2019

GeoJournal

View full text Add to dashboard Cite

show abstract

“…Actualmente, el incremento en el uso de dispositivos móviles ha permitido obtener datos suficientes en otros ámbitos y extender este tipo de estudios también a ciudades de menor tamaño -entre 50 y 100 mil habitantes- (Morstatter et al, 2013;Leontidou et al, 2007;Lansley y Longley, 2016). También, el auge de otras redes sociales -como pueden ser Foursquare, Google Places o Pinterest-, ha permitido ampliar los temas de estudio (Martí, Serrano-Estrada y Nolasco-Cirugeda, 2017;De Vries et al, 2013;Byers, Proserpio y Zervas, 2016;Béjar et al, 2016; García-Palomares, Gutierrez y Mínguez, 2015).…”

Section: Los Datos Generados En Redes Sociales Como Fuente Para El Esunclassified

Los datos geolocalizados de las redes sociales en el estudio de cuestiones urbanas complejas: cinco temas, cinco redes

Ciriquián¹,

Nolasco‐Cirugeda²,

Serrano-Estrada³

2019

ACE: Architecture, City and Environment

View full text Add to dashboard Cite

Geolocated data generated by social networks allow various kinds of urban-related issues to be addressed, broadening knowledge on the different dynamics that occur in the city. This study has a twofold objective: (1) to identify which data variables from five well known social networks-Foursquare, Instagram, Twitter, Google Places and Airbnb-offer potential insights on the study of specific urban phenomena; and, (2) to delve into five exemplary urban topics that can be tackled by analysing the data from these social networks. Methodology Social media are analysed and specific urban issues that can be assessed through their data variables are identified. Specifically, five themes that encompass several research issues are identified through the combination of different data variables. Conclusions Data generated in social networks used for urban study purposes provide a valuable opportunity to address issues such as: [1] the use and preference for certain activities and places; [2] the image and perception of urban spaces; [3] spatiotemporal patterns of people presence and urban space-use; [4] supply and demand of economic activity; and, [5] identification of areas of concentration and specialization in the city. Originality This up to date and easily accessible information provides a thorough picture of complex issues in relation to urban dynamics that, until recently, were not easily measurable and quantifiable. Thus, the interpretation of these data broadens knowledge on city dynamics that can be useful for decision-making processes in the planning and design of the city.

show abstract

“…Moreover, considering the findings of previous studies [29,33,34], we also examine the time-related characteristics of calling activity to reveal the dynamics more clearly. Commonly, daily patterns and intraday patterns are examined to discover time-related characteristics of human behavior, such as calling activity between individuals [43], web browsing activity [35], user activity in virtual worlds [36], Wikipedia editorial activity [37], activity on Twitter and Instagram [38], and spatio-temporal properties of cities in Spain [44]. Motivated by these studies, we apply the k-means method and statistical analysis to examine daily patterns and intraday patterns.…”

Section: Introductionmentioning

confidence: 99%

Dynamics of calling activity to toll-free numbers in China

Gui

Zheng

et al. 2020

PLoS ONE

View full text Add to dashboard Cite

The quantitative understanding of human behavior is a key issue in modern science. Recently, inhomogeneous human activities have been described by bursts (consecutive activities separated by long periods of inactivity) and characterized by fat-tailed inter-event time (interval between two activities) distributions. However, the dynamics between number of activities and activity duration are still unclear. In this study, we analyzed 133 million tollfree call records from China to study the dynamics between call frequency and call duration. We confirmed that both call frequency and call duration exhibit circadian cycles and weekly cycles. By analyzing intraday patterns of these two metrics, we found the opposite volatility and clustered distributions. Results of clustering analysis showed that calling activity to tollfree numbers can be clustered into four clusters. In the "Work" cluster, the distribution of call duration was significantly different from that in the other clusters. The corresponding time of "Work" cluster was much shorter than estimates based on common sense. Intraday patterns and clustering results showed that both call frequency and call duration are primarily related to circadian cycles, the nature of human beings, and that work is a secondary factor that affects these variables. Moreover, we found a strong positive correlation between call frequency and call duration, as well as polarization of joint probability. The polarization indicates two extremes in inhomogeneous calling activity to toll-free numbers, i.e., either people are very busy or very idle. The empirical probability of the extreme was approximately four times that of random probability. Our findings may have great usage for studying the dynamics of inhomogeneous human behavior.

show abstract

Discovery of spatio-temporal patterns from location-based social networks

Cited by 17 publications

References 10 publications

Identifying tourist-functional relations of urban places through Foursquare from Barcelona

Identifying tourist-functional relations of urban places through Foursquare from Barcelona

Los datos geolocalizados de las redes sociales en el estudio de cuestiones urbanas complejas: cinco temas, cinco redes

Dynamics of calling activity to toll-free numbers in China

Contact Info

Product

Resources

About