Presenter: Prof. Dr. Mouzhi Ge, Head of Data Science and Intelligent Systems Research Group, Deggendorf Institute of Technology (DIT), Germany

Abstract: Nowadays, custom hiking trips are designed to cater to travelers' specific desires and user preferences for personalized tourism experiences. With some tourism applications, users can design hiking trips and itineraries that align with their unique interests, such as cultural exploration or sports intentions, or even to avoid crowded places and are easy to navigate. However, as users usually define such hiking trips on the fly, those hiking trips are not being rated and thus suffering from the cold start problem. The user may still want to know the ratings for different features of the self-designed hiking trip such as ratings to the landscape or the route's difficulty. In this talk, we will discuss two proposed solutions to predict the ratings for custom hiking trips from enriched GPS traces. One solution is similarity based and the other one is machine learning based. Both solutions are validated with real-world datasets from Outdooractive and Copernicus. The rating inference in the experiments can be considered a second opinion for custom hiking trips defined by users.

Please note that the seminar will take place at 12:00. Expected duration 30min.

Please note that the presentation will be ONLINE on Zoom:

https://cesnet.zoom.us/j/96798329056?pwd=bENmUUp0T0lFK2M0Z2E3elorR2pIUT09