Multi-Level Visual Similarity Based Personalized Tourist Attraction Recommendation Using Geo-Tagged Photos

TL;DR

This paper introduces MEAL, a multi-level visual similarity approach that leverages geo-tagged photos and self-attention to improve personalized tourist attraction recommendations by better capturing user preferences and photo significance.

Contribution

The paper proposes a novel multi-level visual similarity framework with a quintuplet loss and self-attention mechanism for enhanced tourist attraction recommendation from geo-tagged photos.

Findings

MEAL outperforms existing methods on Flickr dataset.

Multi-level similarity improves the accuracy of user preference modeling.

Self-attention effectively captures photo significance.

Abstract

Geo-tagged photo based tourist attraction recommendation can discover users' travel preferences from their taken photos, so as to recommend suitable tourist attractions to them. However, existing visual content based methods cannot fully exploit the user and tourist attraction information of photos to extract visual features, and do not differentiate the significances of different photos. In this paper, we propose multi-level visual similarity based personalized tourist attraction recommendation using geo-tagged photos (MEAL). MEAL utilizes the visual contents of photos and interaction behavior data to obtain the final embeddings of users and tourist attractions, which are then used to predict the visit probabilities. Specifically, by crossing the user and tourist attraction information of photos, we define four visual similarity levels and introduce a corresponding quintuplet loss to embed the visual contents of photos. In addition, to capture the significances of different photos, we exploit the self-attention mechanism to obtain the visual representations of users and tourist attractions. We conducted experiments on a dataset crawled from Flickr, and the experimental results proved the advantage of this method.