Point-of-interest lists and their potential in recommendation systems

Abstract

Location based social networks, such as Foursquare and Yelp, have inspired the development of novel recommendation systems due to the massive volume and multiple types of data that their users generate on a daily basis. More recently, research studies have been focusing on utilizing structural data from these networks that relate the various entities, typically users and locations. In this work, we investigate the information contained in unique structural data of social networks, namely the lists or collections of items, and assess their potential in recommendation systems. Our hypothesis is that the information encoded in the lists can be utilized to estimate the similarities amongst POIs and, hence, these similarities can drive a personalized recommendation system or enhance the performance of an existing one. This is based on the fact that POI lists are user generated content and can be considered as collections of related POIs. Our method attempts to extract these relations and express the notion of similarity using graph theoretic, set theoretic and statistical measures. Our approach is applied on a Foursquare dataset of two popular destinations in northern Greece and is evaluated both via an offline experiment and against the opinions of local populace that we obtain via a user study. The results confirm the existence of rich similarity information within the lists and the effectiveness of our approach as a recommendation system.

Exploring mobility data for enhancing HIV care engagement in Black/African American and Hispanic/Latinx individuals: a longitudinal observational study protocol

“…Mobility exposures: these data will be used to generate mobility metrics such as total distance travelled, most visited locations and radius of gyration, which measures the average distance a person travels from their most frequent location, such as home or work. Moreover, mobility data will be merged with point of interest (POI) data, a list of specific locations that represents a place such as a landmark or business, 49 to create a timeline of the locations/POIs visited by the participants. The POI data will be compiled from databases of businesses, landmarks and other venues.…”

رصد البصمة الرقمية السياحية ومراكز الأنشطة السياحية من خلال بيانات التوسيم الجغرافي والبيانات المحددة للموقع: مدينة الإسكندرية كدراسة حالة

“…In fact, a comprehensive literature review on the application of big data to tourism has been provided by Li et al (2018) and by Salas-Olmedo et al (2018). More specifically, previous researches on points of interest (POIs) sourced by LBSNs have mainly focused on travel behavior and tourist trajectories in order to provide customized suggestions using TripAdvisor (Van der Zed & Bertocchi, 2018) or Foursquare (Dietz et al 2020;Stamatelatos et al 2021) in conjunction with additional geolocated data (Nolasco-Cirugeda et al, 2022) from social networks, including Twitter or Yelp.…”

Improving Content Retrievability in Search with Controllable Query Generation

“…Another external source of information for entities that was shown to be useful for downstream tasks [54] is the concept of lists, where users group together a number of entities that are similar in a way. In the music domain, this is often referred to as playlists.…”