Host: The Japanese Society for Artificial Intelligence
Name : The 26th Annual Conference of the Japanese Society for Artificial Intelligence, 2012
Number : 26
Location : [in Japanese]
Date : June 12, 2012 - June 15, 2012
In the past, there are a great many research about restaurant recommendation. Most of them focus on location-based methods, and the scenario is usually simple. It's easy to recommend neighboring and price accepted restaurants to people, however, there are very few research considering many event contexts such like purposes, companions, and festivals, etc. In addition to the types of cuisine and price, we even consider the atmosphere and style of restaurants. Unlike the much more extensively researched explicit feedback, we don't have any direct rating from the user regarding their preference. Namely, we lack the substantial evidence on which restaurants user dislike. Contrast to other domains, the lack of booking information is a more severe problem. This research aims at how to use the available data to provide useful recommendation. In this work, we use the data between August of 2008 and December of 2011 from EZTABLE which is an online restaurant booking system in Taiwan, to discover how the event contexts affect restaurant recommendation.
