شبکه های بیزی و توصیه هایی شخصی شده مبتنی بر فرآیند تحلیل سلسله مراتبی برای جاذبه های توریستی بر روی اینترنت
|کد مقاله||سال انتشار||تعداد صفحات مقاله انگلیسی||ترجمه فارسی|
|28769||2009||11 صفحه PDF||سفارش دهید|
نسخه انگلیسی مقاله همین الان قابل دانلود است.
هزینه ترجمه مقاله بر اساس تعداد کلمات مقاله انگلیسی محاسبه می شود.
این مقاله تقریباً شامل 6125 کلمه می باشد.
هزینه ترجمه مقاله توسط مترجمان با تجربه، طبق جدول زیر محاسبه می شود:
Publisher : Elsevier - Science Direct (الزویر - ساینس دایرکت)
Journal : Expert Systems with Applications, Volume 36, Issue 1, January 2009, Pages 933–943
Selecting tourist attractions to visit at a destination is a main stage in planning a trip. Although various online travel recommendation systems have been developed to support users in the task of travel planning during the last decade, few systems focus on recommending specific tourist attractions. In this paper, an intelligent system to provide personalized recommendations of tourist attractions in an unfamiliar city is presented. Through a tourism ontology, the system allows integration of heterogeneous online travel information. Based on Bayesian network technique and the analytic hierarchy process (AHP) method, the system recommends tourist attractions to a user by taking into account the travel behavior both of the user and of other users. Spatial web services technology is embedded in the system to provide GIS functions. In addition, the system provides an interactive geographic interface for displaying the recommendation results as well as obtaining users’ feedback. The experiments show that the system can provide personalized recommendations on tourist attractions that satisfy the user.
Personalized recommendation is one-to-one recommendation through understanding each persona individually (Good et al., 1999 and Resnick and Varian, 1997). Recently personalized recommendation systems have been gaining interest in tourism to assist travelers with travel plans (Loh et al., 2003, Ricci, 2002, Ricci and Werthner, 2002 and Wallace et al., 2003). A travel plan consists of a number of stages, such as choosing destinations, selecting tourist attractions, choosing accommodations, deciding routes, etc. However, at present most of travel recommendations focus on the first stage – suggesting the destinations, with very few exceptions (Ardissono, Goy, Petrone, Signan, & Torasso, 2003). This paper is concerned with the second stage, which suggests a set of tourist attractions in sequence at a given destination. Tourist attractions, which are places intended to attract people to visit at a destination, are often the reason driving travelers to visit destinations (Gunn, 1980, Leiper, 1990, Lew, 1987, Jafari, 2000 and Richards, 2002). There are two challenges in developing a system for personalized recommendations of visiting tourist attractions. One is the integration of heterogeneous online travel information. The other is the semantic matching tourist attractions against travelers’ preferences. First, this recommendation process involves a large amount of detailed up-to-date information of tourist attractions (Ardissono et al., 2003 and Fesenmaier and Jeng, 2000). The information is available over the Internet, published by various travel information providers. However, due to the heterogeneity of the information, it is difficult to automatically integrate the information. Different providers may use different terms to represent the same meaning, or same terms for different meanings. Furthermore, in order to recommend satisfactory tourist attractions to travelers, the characteristics of tourist attractions, for example the activities offered in an attraction, have to match the travelers’ preferences. However, travel preferences are often hidden and are not explicitly known when users start to plan their trips, particularly if visiting an unfamiliar place (Loh et al., 2003 and Viappiani et al., 2002). Thus, in this matching process, two stages are involved: estimating travelers’ preferences, and subsequently evaluating available tourist attractions. In this paper, a system for personalized recommendations of tourist attractions in a travel destination is presented. The system has four main characteristics. First, information of tourist attractions in the destination is obtained by understanding and integrating heterogeneous online information based on a tourism ontology. The ontology contains a set of concepts to express the characteristics of tourist attractions and the relationships between these concepts that the system needs to generate recommendations of tour plans. It is concerned with the services provided at tourist attractions. Second, a Bayesian network is used to estimate the traveler’s preferred activities. With the Bayesian network, travel behavior of the person and of other travelers who have similar taste can be combined. Third, the analytic hierarchy process (AHP) is used to rank the available tourist attractions because of its capability of using the traveler’s travel behavior in the past. Finally, spatial web services technology is used to incorporate on-demand mapping and spatial functionality into the system. The rest of this paper is organized as follows. Section 2 describes the ontological modeling of the information of tourist attractions. The estimation of the traveler’s preferred activities using a Bayesian network and ranking the tourist attractions using AHP are discussed in Sections 3 and 4, respectively. Section 5 describes embedding GIS functions using spatial web services. The architecture of the system and its implementation are presented in Section 6. Finally, the summary of this research is discussed in Section 7.
نتیجه گیری انگلیسی
In this paper, an intelligent recommendation system is presented. The system offers the personalized recommendations of tourist attractions at a given destination. By applying ontology theory, Bayesian network, AHP, and spatial web service technology, this system leads to more intelligence, collaboration, and personalization in recommendations of tourist attractions. In summary, the system has the following features: