Paper
Presentation Slides
Quantifying event interestingness in Event-Based Social Networks is crucial to filter for compelling events. However, because interestingness is inherently subjective, it is impossible to universally define. We propose a set of features based on the event description as well as the RSVP history of related events that indicate interesting events. Furthermore, we introduce a method to combine them to an interestingness score that is derived from user-specified preferences. The details of our implementation are provided in the paper above. The functioning web application prototype as a proof of concept can be seen from the video below.
This project was done by Maximilian Grundke, Jaeyoon Jung, Jan Philipp Sachse, and Georg Wiese.