الفهرس 
INTRODUCTIONOnly 14 pages are availabe for public view
 |  | from | 98 |  |  |
| | | from | 98 | | |
Abstract
Trajectory data analysis has recently become an active research area.
This is due to the large availability of mobile tracking sensors, such as
GPS-enabled smart phones. However, those GPS trackers only provide
raw trajectories (x, y, t), ignoring information about the geographical locations, transportation mode, etc. This information can contribute in
producing significant knowledge about movements, which transforms
raw trajectories into semantic trajectories. Therefore, research lately has focused on semantic trajectories; their representation, construction, and applications. Furthermore, advances in location acquisition and mobile technologies also led to the addition of the location dimension to Social Networks (SNs) and to the emergence of a newer class called Locationbased Social Networks (LBSNs). One of the key applications of semantic trajectories is location-based recommendation, which is a main function of LBSNs.
This research investigates the current studies on semantic trajectories so far. We propose a new classification schema for the research efforts in
semantic trajectory construction and applications. The proposed classification schema includes three main classes: semantic trajectory modeling, computation, and applications. Additionally we proposed a methodology to semantically enhance LBSNs through extracting SN Geo-tagged
media annotations and using them as location semantics. This enabled us to introduce an Interest Aware Location-based Recommender System (IALBR) which combines the advantages of both LBSNs and SNs, in order to provide interest aware location-based recommendations. This recommender system is proposed as an extension to LBSNs. It is novel in: 1) utilizing the Geo-content in both LBSNs and SNs, 2) ranking the recommendations based on a novel scoring method that maps to the user interests. It also works for passive users who are not active content contributors to the LBSN. This feature is critical to increase the number of LBSN users. Moreover, it helps in reducing the cold start problem, which is a common problem facing the new users of recommender systems who get random unsatisfying recommendations. This is due to the lack of user interests awareness, which is reliant on user history in most of the recommenders.
We evaluated the IALBR system with a large-scale real dataset collected
from foursquare in respect of precision, recall & f-measure. We
also compared the results with yelp, as a ground truth system, using metrics like the Normalized Discounted Cumulative Gain and the Mean Absolute Error. In comparison to the baseline (i.e.Foursquare), the IALBR recommended on average 3 times more venues with a precision of 80% and achieved an F-measure of 0.87 (at N=15). In comparison to Yelp ratings, the IALBR scored an MAE of 1.3 and an NDCG of 0.9.