Point-of-Interest Recommendation in Location-Based Social Networks by Shenglin Zhao & Michael R. Lyu & Irwin King

Author:Shenglin Zhao & Michael R. Lyu & Irwin King
Language: eng
Format: epub
ISBN: 9789811313493
Publisher: Springer Singapore

3.5.1 Data Description and Experimental Setting

Two real-world datasets are used in the experiment: one is Foursquare data from January 1, 2011 to July 31, 2011 provided in [6] and the other is Gowalla data from January 1, 2011 to September 31, 2011 in [35]. We filter the POIs checked-in by less than 5 users and then choose users who check-in more than 10 times as our samples. After the preprocessing, the datasets contain the statistical properties as shown in Table 3.1. We randomly choose 80% of each user’s check-ins as training data, and the remaining 20% for test data. Moreover, we use each check-in (u, t, l) in training data to learn the latent features of user, time, and POI. Then given the (u, t), we estimate the score value of different candidate POIs, select the top N candidates, and compare them with check-in tuples in test data.Table 3.1Statistics of datasets

Download

Copyright Disclaimer:
This site does not store any files on its server. We only index and link to content provided by other sites. Please contact the content providers to delete copyright contents if any and email us, we'll remove relevant links or contents immediately.