Proceedings:
RecSys '20: Fourteenth ACM Conference on Recommender Systems. Virtual Event. Brazil. September, 2020
Publisher:
Association for Computing Machinery, New York, United States
Abstract:
We present PicTouRe-a picture-based tourism recommender. PicTouRe aims to mitigate people´s difficulties in explicitly expressing their touristic preferences, which is even more challenging in the initial phase of travel decision making. Addressing this issue, with PicTouRe we follow the idiom "a picture is worth a thousand words" and use pictures as a tool to implicitly elicit peoples´ touristic preferences. We describe the core concept of PicTouRe-the Generic Profiler, which in essence determines an explainable vector representation, ie, touristic profile, given any picture collection as input. We showcase a user´s journey through PicTouRe and describe the steps behind. Finally, we present results of a first user study supporting our approach. PicTouRe is available under https://pictoprof. ec. tuwien. ac. at and a demo video under https://youtu. be/xZnXLPcenEs.
TU Focus:
Information and Communication Technology
Info Link:
https://publik.tuwien.ac.at/showentry.php?ID=294079&lang=1
Author List:
M. Sertkan, J. Neidhardt, H. Werthner