Skip to Content
You are currently on the new version of our website. Access the old version .
ElectronicsElectronics
  • Article
  • Open Access

11 February 2025

30 Pages

Improving Location Recommendations Based on LBSN Data Through Data Preprocessing

,
and
Institute of Computer Science, Warsaw University of Technology, Nowowiejska 15/19, 02-665 Warsaw, Poland
*
Author to whom correspondence should be addressed.

Abstract

The accurate prediction of the next location in a sequence is highly beneficial for users of mobile applications. In this study, we investigate how various data preprocessing techniques affect the performance of location recommendation systems. We utilize datasets from Foursquare and Twitter, incorporating users’ historical check-ins. Key preprocessing steps include filtering datasets to users with common features, analyzing user location preferences, varying sequence lengths and location categories, and integrating time-of-day information. Our findings reveal that proper data preprocessing significantly enhances the accuracy of recommendations by addressing key challenges such as data sparsity and user heterogeneity. Specifically, tailoring datasets to individual user attributes improves model personalization, while restructuring category hierarchies balances precision and diversity in the recommendations that are given. Integrating temporal data further refines the predictions that are made by accounting for time-based user behavior. Recommendations are generated using recurrent neural networks (RNNs) and hidden Markov models (HMMs), with the experimental results showing up to 20% improvement in the precision of personalized models compared to global ones.

Article Metrics

Citations

Article Access Statistics

Multiple requests from the same IP address are counted as one view.