Exploiting Location-Based Context for POI Recommendation When Traveling to a New Region

Abstract

Traveling to a new region has become a very common thing for people, due to work or life requirement. With the development of recommendation engine and the popularity of social media network, people are more and more used to relying on personalized Points-of-Interest (POI) recommendations. However, traditional approaches can fail if users moves to a region where they had little or no active history or even social network friends information before. Under the requirement of smart city construction, the need to give high quality personalized POI recommendation when a user travels to a new region has arisen. Fortunately, with the widespread of wireless Internet, the booming of Internet-of-Things (IoT) and the common-usage of location sensors in mobile phones, the coupling degree between social media networks and location information is ever increasing, which could leads us to a new way to solve this problem in the ear of Big Data. In this research, we presented New Place Recommendation Algorithm (N-PRA) which is designed based on Latent Factor model. Many different types of social media contexts (time-related and location-related), such as a user's interest fluctuation, different types of POIs' popularity fluctuation, types of POIs, the influence of geographical neighborhood on POIs, and user's social network friendship are taken into consideration in this approach. The algorithm presented is verified on Yelp, an open-source real urban data-set, and compared against several other baseline POI recommendation algorithms. Experimental results show that the algorithm presented in this paper could achieve a better accuracy.

Temple Recommendation Engine for Route Planning Based on TPS Clustering CNN Method

“…For example, users can share their current location on websites, upload geotagged photos to social media platforms, and write reviews about places they have visited. Location is therefore considered one of the key elements of user context, and in-depth knowledge of user behavior and interests can be derived from user location data [24].…”

A Survey on Recommender Systems for Internet of Things: Techniques, Applications and Future Directions

“…The lack of information (the cold start problem) is the main issue in this situation. In [41], the authors designed an algorithm that has the ability to tackle this issue by considering the users' location history and user reviews information.…”

Context-Induced Activity Monitoring for On-Demand Things-of-Interest Recommendation in an Ambient Intelligent Environment

“…Although the collaborative filtering approach has been adapted in numerous studies [16][17][18][19], there are potential shortcomings that make it inefficient for RSIoT particularly, in terms of large amount of data, cold start problem, and data sparsity. In content-based, instead of relying on ratings, it recommends items that are similar to the items previously targeted by the user [20].…”