High quality product data is a necessary prerequisite for supporting efficient browsing and recommendation procedures on e-commerce platforms. This is especially true for the tourism domain where an abundance of information can easily overwhelm users. Although classification data such as to which category (e.g. accommodation, restaurant or sight) a tourism product belongs is usually directly available, qualitative information, such as proximity to a lake or opportunities for dining or shopping, is rarely provided in a structured way. As a consequence, users can not restrict their search on these criteria; rather, it would require costly manual information acquisition efforts. In this paper we propose a knowledge-based approach that automatically associates such qualitative concepts with tourism products based on their geographic coordinates and their spatial proximity. An initial evaluation of the approach that considered automatically generated annotations within different regions suggests that it can be used as an alternative to domain experts.
The increasing plethora of information available on the Web necessitates effective personalization mechanisms that allow users to retrieve pieces of information that are more likely to be of interest to them. Fortunately, the democratization of the Web (aka. Web 2.0) that provides online users with widely available tools that allow them contribute and integrate themselves into the global information space not only increases the sheer amounts of data, but also offers opportunities to extract semantic meaning.This paper therefore presents an integrated approach that harnesses geo-tagged web resources like tourism services or track data from bike trails to derive semantic annotations for objects from their geographic proximity. Following this, a recommendation mechanism is proposed that hybridizes collaborative mechanisms with the additional knowledge about semantic annotations to make predictions about what will be relevant to a user in a specific situation. The utility of this integrated approach is showcased by an adaptive Web-GIS scenario that supports travelers in their decision making. Finally, the proposed algorithms are evaluated using historical log data from real users who were exploring the map of a tourism destination. The results indicate that, despite very short interaction sequences, improvements compared to a collaborative filtering baseline can be achieved. An additional advantage lies in offering users more detailed options to express their search preferences that is not quantified by the presented evaluation scenario.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.