User Preferential Tour Recommendation Based on POI-Embedding Methods

TL;DR

This paper introduces a personalized tour recommendation algorithm that uses POI-embedding techniques to generate itineraries aligned with user preferences and constraints, demonstrated on Flickr data from four cities.

Contribution

The paper presents a novel POI-embedding based recommendation algorithm that models tour planning as a word embedding problem, improving personalization and constraint satisfaction.

Findings

High recall, precision, and F1-score in preliminary tests

Effective personalization based on user trajectories

Improved itinerary relevance and accuracy

Abstract

Tour itinerary planning and recommendation are challenging tasks for tourists in unfamiliar countries. Many tour recommenders only consider broad POI categories and do not align well with users' preferences and other locational constraints. We propose an algorithm to recommend personalized tours using POI-embedding methods, which provides a finer representation of POI types. Our recommendation algorithm will generate a sequence of POIs that optimizes time and locational constraints, as well as user's preferences based on past trajectories from similar tourists. Our tour recommendation algorithm is modelled as a word embedding model in natural language processing, coupled with an iterative algorithm for generating itineraries that satisfies time constraints. Using a Flickr dataset of 4 cities, preliminary experimental results show that our algorithm is able to recommend a relevant and accurate itinerary, based on measures of recall, precision and F1-scores.