|ognizant Communication Corporation|
INFORMATION TECHNOLOGY & TOURISM
VOLUME 6, NUMBER 3
Information Technology & Tourism, Vol. 6, pp. 157-165
1098-3058/04 $20.00 + .00
Copyright © 2004 Cognizant Comm. Corp.
Printed in the USA. All rights reserved.
A Tourism Recommender System Based on Collaboration and Text Analysis
Stanley Loh,1,2 Fabiana Lorenzi,2 Ramiro Saldaña,1 and Daniel Licthnow1
1Catholic University of Pelotas (UCPEL), R. Félix
da Cunha, 412-Pelotas, RS Brazil, 96010-000
2Lutheran University of Brazil (ULBRA), R. Miguel Tostes, 101-Canoas, RS Brazil, 94420-280
This work presents a recommender system that helps travel agents in discovering options for customers, especially those who do not know where to go and what to do. The system analyzes textual messages exchanged between a travel agent and a customer through a private Web chat. Text mining techniques help discover interesting areas in the messages. After that, the system searches a database and retrieves tourist options (like cities and attractions) classified in these interesting areas. The system makes use of a tourism ontology, containing themes and a controlled vocabulary, to identify themes in the textual messages. The system acts as a decision support system, because it does not make recommendations directly to the customer.
Key words: Collaboration; Tourism; Text mining; Recommender systems; Decision support systems
Address correspondence to Stanley Loh, Catholic University of Pelotas (UCPEL), R. Félix da Cunha, 412-Pelotas, RS Brazil, 96010-000. E-mail: email@example.com
User-Oriented Evaluation of a Natural Language Tourism Information System
Helmut Berger,1 Michael Dittenbach,1 and Dieter Merkl1,2
1Electronic Commerce Competence Center-EC3, Donau-City-Straße
1, A-1220 Wien, Austria
2Institut fur Softwaretechnik, Technische Universität Wien Favoritenstraße 9-11/188, A-1040 Wien, Austria
This article presents a query interface exploiting the intuitiveness of natural language for the largest Austrian Web-based tourism platform Tiscover. The results and our insights from analyzing the natural language queries collected during a field trial in which the interface was promoted via the Tiscover homepage are also described. This analysis shows how users formulate queries when their imagination is not limited by conventional search interfaces with structured forms consisting of check boxes, radio buttons, and special-purpose text fields. As another aspect of user-oriented evaluation of the natural language system, a usability study focusing on a comparison of a conventional search interface with the natural language approach was performed. The results of this field trial as well as the findings of the usability study are thus valuable indicators into which direction the Web-based tourism information system should be extended to better serve the customers.
Key words: Tourism information system; Natural language processing; User behavior study
Address correspondence to Helmut Berger, Electronic Commerce Competence Center-EC3, Donau-City-Straße 1, A-1220 Wien, Austria. E-mail: firstname.lastname@example.org
Intelligent One-Stop-Shop Travel Recommendations Using an Adaptive Neural Network and Clustering Of History
Manolis Wallace,1 Ilias Maglogiannis,2 Kostas Karpouzis,1 George Kormentzas,2 and Stefanos Kollias1
1Image, Video and Multimedia Systems Laboratory, Department
of Electrical and Computer Engineering, National Technical University of
2Department of Information and Communication Systems Engineering, University of the Aegean
The rapid growth of e-commerce during the last years has obliged a significant number of companies and professionals from diverse fields to turn to the Internet as a medium through which they aim to promote their products and services. A main issue for product and service providers is that, as this new market is characterized by the lack of personal contact, it is difficult to offer personalized services to end users; it is this type of service that end users look for and remain faithful to. Recommender systems belong to a new breed of software that aims to fill this gap; they rely on the analysis of past user actions to estimate the optimal way with which to interact with each user. In this article we explain why existing recommender systems are not adequate to provide for efficient personalization of interaction in the area of travel services, as they cannot support the user in all the phases of travel planning, and propose a new scheme to overcome the identified difficulties. Our approach considers the relation between different types of services in the usage history of the system. It is based on a hierarchical clustering of usage history to extract meaningful usage patterns, as well as an adaptive neural network structure that allows for online adaptation to the user, and enables the offering of intelligent recommendations.
Key words: Recommender systems; Travel planning; Collaborative user modeling; Hierarchical clustering; Neural network; Linear adaptation
Address correspondence to Ilias Maglogiannis, University of the Aegean, Department of Information and Communication Systems Engineering, 83200 Karlovasi, Greece. Tel: +30-2273-82239; Fax: +30-2273-82009; E-mail: email@example.com
An Automated Itinerary Planning System for Holiday Travel
Simon Dunstall, Mark E. T. Horn, Philip Kilby, Mohan Krishnamoorthy, Bowie Owens, David Sier, and Sylvie Thiebaux
CSIRO Mathematical and Information Sciences
This article describes a prototype travel recommender system called the Electronic Travel Planner (ETP), which prepares travel itineraries for tourists. The system is driven by models of a traveler's preferences and requirements, and makes reference to databases containing information pertaining to tourism and travel products. Its main tasks are to select destinations for the traveler to visit, to decide which tours or attractions are to be taken, and to compose a detailed itinerary linking up the chosen components. These tasks entail difficult optimization problems, which the prototype addresses by means of an heuristic problem-solving framework. Computational tests confirm the effectiveness of the methods used, and suggest that an automated approach will be feasible in full-scale travel planning applications.
Key words: Traveler recommender systems; Journey planning; Routing; Scheduling; Optimization
Address correspondence to Mark E. T. Horn, GPO Box 664, Canberra ACT 2601, Australia. Tel: +61 2 6216 7054; Fax: +61 2 6216 7111; E-mail: firstname.lastname@example.org
Socially Enhanced Travel Booking: A Case Study
Åsa Rudström and Petra Fagerberg*
Swedish Institute of Computer Science, SICS, Box 1263, 164 29 Kista, Sweden
The ability to obtain user data in an unobtrusive way is instrumental to the success of recommendations based on collaborative data. In a travel booking scenario, where data about the current user were sparse, a solution based on displaying booking statistics was proposed. A prototype system was built in a joint project with the international transport and travel service company Stena Line. A qualitative user evaluation provided support for two hypotheses: 1) that displaying statistics of other travelers' booking choices would support users in the booking process, and 2) that users would form their own recommendations if presented with background information.
Key words: Online travel booking; Recommender system; Collaborative recommendation; Social computing; Social navigation
*Currently at the IT University in Stockholm, Department of Computer and Systems Sciences.
Address correspondence to Åsa Rudström, SICS, Box 1263, 164 29 Kista, Sweden. Tel: +46 70 7748832; Fax: +46 8 751 7230; E-mail: email@example.com