Talking Places: Modelling and Analysing Linguistic Content in Foursquare

Abstract

Abstract-The advent of online social media and the growing popularity of sensor-equipped mobile devices have created a vast landscape of location-aware applications and services. This goldmine of data, including temporal and spatial information of unprecedented granularity, can help researchers gain insights into the behavioural patterns of people at a global scale. Here we analyse the textual content of millions of comments published alongside Foursquare user check-ins. For this, we extend a standard topic modelling approach so that it explicitly takes into account geographic and temporal side information. The framework is applied to Foursquare data and used to detect the dominant topics in the neighbourhoods of a city. In particular, we present the most prominent topics discussed by Foursquare users in New York, London, Chicago and San Francisco. We characterize the topics' spatial coverage and temporal evolution, and we also highlight some cultural idiosyncrasies. Finally, we evaluate the novel spatio-temporal topic model quantitatively. We believe that our model may be a useful tool for social scientists and application developers.

Latent Dirichlet allocation (LDA) and topic modeling: models, applications, a survey

“…In [128] introduced a method that leads the machine translation systems to relevant translations based on topic-specific contexts and used the topic distributions to obtain In [127] presented a diversity of new visualization techniques to make the concept of topic-solutions and introduce new forms of supervised LDA, to evaluate they considered a corpus of dissertation abstracts from 1980 to 2010 that belongs to 240 universities in the United States. In [126] developed a standard topic modeling approach, that consider geographic and temporal information and this approach used to Foursquare data and discover the dominant topics in the proximity of a city. Also, the researchers have shown that the abundance of data available in location-based social network (LBSN) enables such models to obtain the topical dynamics in urbanite environments.…”

VGDI – Advancing the Concept: Volunteered Geo‐Dynamic Information and its Benefits for Population Dynamics Modeling

“…Activity categories in VGI are themselves user‐generated, which therefore allows individualized and in a collective or clustered sense social and cultural patterns to materialize in spatially‐explicit form (Phithakkitnukoon and Olivier ; Arribas‐Bel et al ). This includes region‐ and culture‐specific differences that affect activity patterns not only spatially but also and in particular temporally (Bauer et al ). Weekends, as generalized in European countries, are commonly understood to have different activity patterns from work days.…”

Who, Where, When, and What

“…Specifically, they assume that each word is drawn from a background word distribution, a time and location dependent topic, or a topic of the documents. Similarly, Bauer et al [2012], propose an LDA-based spatiotemporal model, where a city is divided into grids. Compared with the models of Mei et al [2006] and Bauer et al [2012], our model considers more aspects: (1) the models Mei et al [2006] and Bauer et al [2012] do not consider the user information at all; (2) it either does not consider the geographic property of locations [Mei et al 2006], or does not consider the functions of locations [Bauer et al 2012]; and (3) they only consider discretized time.…”