A TOURISM RECOMMENDER SYSTEM BASED ON COLLABORATION AND TEXT ANALYSIS
Stanley Loh, Fabiana Lorenzi, Ramiro Saldaña, Daniel Licthnow · Information Technology & Tourism · 2003
This work presents a recommender system that helps travel agents in discovering options for custom-ers, especially those that 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 sys-tem 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 travel agent, a person with knowledge and capabili-ties to provide such advice. However, recommenda-tions from these agents may be restricted by human factors, such as lack of memory, limited knowledge about the world, countries, or cities and their tourist options, which could result in poor capacity to match a tourist’s requirements or wishes against the options stored in a database. Sometimes the final decision is much too dependent on the travel agent. A recommender system is software to aid in the social process of indicating or receiving indication about what options are better suited in a special case for a certain individual (Resnick & Varian, 1997).