Article Preview
Top1. Introduction
A new paradigm of internet based digital support systems has been introduced as recommender systems with the rising frequency in the utility of GPS enabled smart devices, and the increasing popularity of Location Based Social Networks (LBSN) such as Foursquare and Facebook (Logesh and Subramaniyaswamy, 2017a). On daily basis, we are exposed to a plethora of geo-spatial data that not only makes as be aware of our own location, but able to digitally mark our locations as digital foot prints and share our experience on those places to the online social community. Since the geo-spatial locations are mainly coordinates of temporal and spatial features that generally associated with a latitude and longitude we can extract this information and use it to interpret and understand their affinities of travel towards a particular set of Point of Interests (Logesh et al., 2017a; Logesh and Subramaniyaswamy, 2017b). With the help of user's existing travel pattern, personalized travel recommender system considers the similarities between user’s interests and the current context for the tailored travel recommendations (Logesh and Subramaniyaswamy, 2016).
In this article, we present a novel travel recommender system to help active target user by providing tailored travel recommendations incorporating the most efficient travel trajectory between one location to another based on crowd-sourced digital-footprints shared from an LBSN called Foursquare. At every minute, a massive amount of geo-spatial data is being shared as user’s location in the form of check-ins on the LBSNs to express their experience about that location.
In the existing travel recommender systems, the main focus is on two specific points alone and the travel path is accounted only between the starting and the ending location (Logesh et al., 2017b; Logesh et al., 2017c). As an extensive enhancement, in we aim to contribute a new travel recommender system that not just deals with two location points alone but also generate multiple POIs. With the help of LBSN, a profile is generated for the active target user by taking account of travel history and evaluating the most frequently visited locations. A comparison is made against similar location sets of various users of the user base to provide an efficient and personalized travel recommendation based on the interests of the user.