Multi-Level Visual Similarity Based Personalized Tourist Attraction Recommendation Using Geo-Tagged Photos
This work addresses the need for more accurate travel recommendations for users by enhancing visual content analysis, though it is incremental in nature.
The paper tackled the problem of personalized tourist attraction recommendation by proposing a multi-level visual similarity method (MEAL) that uses geo-tagged photos and interaction data to predict visit probabilities, achieving improved performance as evidenced by experimental results on a Flickr dataset.
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.