As a guest user you are not logged in or recognized by your IP address. You have
access to the Front Matter, Abstracts, Author Index, Subject Index and the full
text of Open Access publications.
Most of the existing works on travel recommendations are based on check-in data or photos. From a distinct point of view, the present research pays attention to network travelogues that contain a large number of users' evaluation information on tourism items. By analyzing the sentiment inclinations, demographic information and user's web access actions, a hybrid user interest model based on ontology is established. When a query is submitted, neighbors who have similar sentiment inclinations are found by this model, and then the interest degree of tourism items that are located in the same category of target query item can be predicted according to the user's historical behavior. The results show that our hybrid ontology model can make tourism item recommendations more effectively than the standard or pure ontology models, and better solve the cold start problem.
This website uses cookies
We use cookies to provide you with the best possible experience. They also allow us to analyze user behavior in order to constantly improve the website for you. Info about the privacy policy of IOS Press.
This website uses cookies
We use cookies to provide you with the best possible experience. They also allow us to analyze user behavior in order to constantly improve the website for you. Info about the privacy policy of IOS Press.