Natural language processing applied in itinerary recommender systems

Authors:
Andreea Diosteanu;Liviu Adrian Cotfas;Alexandru Smeureanu;Stefan Daniel Dumitrescu
Affiliations:
The Bucharest Academy of Economic Studies, Bucharest, Romania;Economic Informatics, The Bucharest Academy of Economic Studies, Bucharest, Romania;Economic Informatics, The Bucharest Academy of Economic Studies, Bucharest, Romania;Computers and Information Technology, Politehnica University of Bucharest, Bucharest, Romania
Venue:
ACACOS'11 Proceedings of the 10th WSEAS international conference on Applied computer and applied computational science
Year:
2011

Citing 6
Cited 0

Cyberguide: a mobile context-aware tour guide

Wireless Networks - Special issue: mobile computing and networking: selected papers from MobiCom '96
The role of adaptive hypermedia in a context-aware tourist GUIDE

Communications of the ACM - The Adaptive Web
Yago: a core of semantic knowledge

Proceedings of the 16th international conference on World Wide Web
A Personalized Tourist Trip Design Algorithm For Mobile Tourist Guides

Applied Artificial Intelligence
Neural based approach to keyword extraction from documents

ICCSA'03 Proceedings of the 2003 international conference on Computational science and its applications: PartI
Near-optimal personalized daily itineraries for a mobile tourist guide

ISCC '10 Proceedings of the The IEEE symposium on Computers and Communications

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper we present a mobile application based on a hybrid multi-objective genetic algorithm and Natural Language Processing that can be used by tourists to smartly generate itineraries. Besides allowing users to find interesting Points of Interest based on highly detailed information, the semantic search approach is also capable of providing recommendation without requiring a lot of information regarding the current user. A multi-objective genetic algorithm has been used in order to find Pareto-optimal solutions in near real-time for the itinerary problem. The proposed system requires minimum input from the user and it is easy to use, thus we can state that our solution is both complex and at the same time user-oriented.