Institutional Repository [SANDBOX]
Technical University of Crete
EN  |  EL

Search

Browse

My Space

Content-based recommendations using similarity distance measures with application in the tourism domain

Ziogas Ioannis-Panagiotis, Streviniotis Errikos, Papadakis Harris, Chalkiadakis Georgios

Full record


URI: http://purl.tuc.gr/dl/dias/67B9A36C-D414-4469-B473-CFA10E45A9DB
Year 2022
Type of Item Conference Full Paper
License
Details
Bibliographic Citation I.-P. Ziogas, E. Streviniotis, H. Papadakis and G. Chalkiadakis, “Content-based recommendations using similarity distance measures with application in the tourism domain,” in Proceedings of the 12th Hellenic Conference on Artificial Intelligence (SETN 2022), Corfu, Greece, 2022. doi: 10.1145/3549737.3549772. https://doi.org/10.1145/3549737.3549772
Appears in Collections

Summary

In this paper, we explore the use of similarity distance measures for Content-based recommendations for touristic attractions. First, we study ways of deploying hierarchies of points of interests (POIs) and operate upon them with well-known similarity distance measures originating in the text analysis domain. Then, we progressively build three novel, hierarchy-free, similarity measures, and discuss their strengths and weaknesses. We end up with a measure, the Weighted Extended Jaccard Similarity (WEJS) that combines information regarding the user interests (in the form of user preference-related weights applied on the items’ features) and specific items’ characteristics (in the form of particular values for the items’ features). As such, the use of WEJS allows the provision of recommendations that are effectively personalized. Interestingly, though it is a hierarchy-free measure, it is able to recommend items based on others that would naturally appear close in a features-based POIs hierarchy; while at the same time it is able to capture similarities among items that would be distant to each other in any hierarchy built solely based on the POIs’ features. Our systematic experimental evaluation on a real-world dataset showcases the benefits and limitations of the various measures, and confirms the effectiveness of WEJS in offering “rich” and personalized recommendations.

Services

Statistics