Personalized itinerary recommendation: Deep and collaborative learning with textual information

Abstract

Personalized itinerary recommendation is a complicated and challenging task, which aims to construct and recommend a visit sequence consists of multiple Points of Interest (POIs) with the constraints that maximizing user satisfaction while adhering time budget. User interests, therefore, becomes the most crucial element in the recommendation task, determining the POIs and their visit durations in the itinerary. In this paper, we propose a novel framework named DCC-PersIRE to infer the user interests and recommend personalized itinerary consists of POIs, visit durations and visit sequence. Specifically, we employ an unsupervised deep learning model to embed the POI textual contents, and then propose a DCC model, which seamlessly integrates the embedded POI textual contents with the traditional and widely used user-POI visits and POI categories, to predict the user interests as well as the visit durations. Then, after formulating itinerary construction as a variant of the Orienteering Problem, an Iterated Local Search based algorithm is proposed to calculate the visit sequence with maximized satisfaction consists of multiple POIs and personalized POI visit durations, i.e., the optimal itinerary. Extensive experiments on eight real-world datasets validate the effectiveness of DCC-PersIRE. The experimental results show that our algorithm delivers a more fine-grained prediction of user interests and outperforms various state-of-the-art baselines in tour itinerary recommendation.