Region Of Interest(ROI) Recommendation System

  • 鄭 貝思

Student thesis: Master's Thesis


In these years Location-Based Social Network LBSN becomes more and more popular A platform for users to share their visits and experiences through check-ins records is provided and thereby many applications are being developed Travel recommendation system is actually one of them Users normally visit the spots in groups when they travel They will only move to the next travel area after visited all their favorite spots and some nearby attractions in one area We call this Region Of Interest (ROI) The recent travel recommendation systems (Point Of Interest POI Recommendation) normal recommend the spots in amount of K to the users by the TOP-K calculation method Users need to plan their trips from these results themselves The POI Recommendation system does not help the users to plan a prefect visiting schedule entirely and thus cannot fulfill the purpose of personalized visiting schedule planning Moreover POIs recommended by the POI recommendation system are always too far away of each other or unsuitable for traveling The planned schedules with these results are inaccurate Therefore we propose a scenic spot recommendation system which uses the LBSN's check-ins records to count every single-day schedule of the trips in different days in the offline section Then divide the scenic spots in areas according to the days of trip by distance probability and map Finally recommend the suitable attraction areas to the users according to their preferences and the popularity of the attraction areas in the online section So that such system is more in line with the two original intentions of the travel recommendation system: (1) in line with the users’ traveling behavior (2) time-saving and personalized schedule planning
Date of Award2018 Aug 9
Original languageEnglish
SupervisorChiang Lee (Supervisor)

Cite this