Predicting Venue Popularity Using Crowd-Sourced and Passive Sensor Data

Abstract

Efficient and reliable mobility pattern identification is essential for transport planning research. In order to infer mobility patterns, however, a large amount of spatiotemporal data is needed, which is not always available. Hence, location-based social networks (LBSNs) have received considerable attention as a potential data provider. The aim of this study is to investigate the possibility of using several different auxiliary information sources for venue popularity modeling and provide an alternative venue popularity measuring approach. Initially, data from widely used services, such as Google Maps, Yelp and OpenStreetMap (OSM), are used to model venue popularity. To estimate hourly venue occupancy, two different classes of model are used, including linear regression with lasso regularization and gradient boosted regression (GBR). The predictions are made based on venue-related parameters (e.g., rating, comments) and locational properties (e.g., stores, hotels, attractions). Results show that the prediction can be improved using GBR with a logarithmic transformation of the dependent variables. To investigate the quality of social media-based models by obtaining WiFi-based ground truth data, a microcontroller setup is developed to measure the actual number of people attending venues using WiFi presence detection, demonstrating that the similarity between the results of WiFi data collection and Google “Popular Times” is relatively promising.

Explaining demand patterns during COVID-19 using opportunistic data: a case study of the city of Munich

“…Similarly, a large number of reviews by customers could be indicative of latent characteristics of a POI. These features such as rating and number of posted reviews are also used in modeling the demand trend modeling [ 30 , 32 ]. It is pertinent to mention that other demographic factors, such as average income in the locality, could also play an essential role in the retail consumption [ 33 ], but the same is not considered in this study because such a dataset was not available.…”

“…Herein we check the significance of covariates in explaining the day-specific popularity before and during the lockdown. Previous studies such as [ 32 ] and [ 30 ] have also modeled popularity as a dependent variable in regression formulation. The dependent variable is the day-specific popularity of a POI, which is to be mapped to a set of explanatory variables, represented analytically as follows: …”

“…However, these models depend heavily on the explicit analytical formulation and thus could introduce model-bias. To counter this, we use regularized Gradient Boosting (GB) [ 46 ] for regression, inspired by previous studies [ 30 ]. GB, a machine learning technique, is based on training weak learners in an additive manner.…”

“…These data are primarily collected from smartphone applications, in which the user’s location history is enabled, such as geotagged data or Location-Based Social Networks (LBSNs). Geotagged tweets [ 27 ], Foursquare check-ins [ 28 ], and popularity trends [ 29 , 30 ] are some examples of such data that capture the spatial-temporal evolution of the demand and have already shown their utility in previous studies. Specifically, popularity trends have been used, to predict venue popularity [ 30 ], calculate demand expansion factors [ 31 ], classify activities [ 29 ] and investigate consumer behaviors [ 32 ].…”

“…Geotagged tweets [ 27 ], Foursquare check-ins [ 28 ], and popularity trends [ 29 , 30 ] are some examples of such data that capture the spatial-temporal evolution of the demand and have already shown their utility in previous studies. Specifically, popularity trends have been used, to predict venue popularity [ 30 ], calculate demand expansion factors [ 31 ], classify activities [ 29 ] and investigate consumer behaviors [ 32 ]. These varied applications of POI demand patterns from popularity trends suggest their potential in other unexplored avenues, such as disruptive events.…”