Turist@: Agent-based personalised recommendation of tourist activities

Abstract

Recommender systems in e-Tourism normally focus on helping tourists to select appropriate destinations. A related problem that has been less explored in the literature is how to provide personalised recommendations of cultural and leisure activities when the tourist has already arrived at the destination. This paper presents a novel recommendation system, Turist@, which addresses this issue. Its agent-based modular design permits to model different kinds of activities in a flexible way, and allows the implementation of a location-aware front-end in the mobile device of the user. Special care has been put in the recommendation engine, implemented via a specialised Recommender Agent. It incorporates a mixture of content-based and collaborative recommendation strategies, thus avoiding the drawbacks of each individual method, and is able to perform recommendations in heterogeneous scenarios. Recommendations take into account user profiles which are implicitly updated after the analysis of user actions (e.g., queries, evaluations). The system has been successfully deployed and tested in the World Heritage-listed city of Tarragona.

Introduction

Tourism has experienced an enormous growth in recent years, motivated, in part, for the fast development of information and communication technologies and the global spread of Internet (Alptekin & Büyüközkhan, 2011), which have eased the access to large amounts of information about destinations, points of interest and travelling plans to potential tourists all around the world. Nowadays, e-Tourism (Castillo et al., 2008) enjoys a great success both from an economic and a social perspective. Many electronic sites and Web portals offer up-to-date information which is massively used by tourists to select destinations and plan their trips. Due to the obvious interest of both tourists and destination providers in selecting enjoyable destinations, and taking into account the overwhelming amount of information available through the Web, many recommender systems have been developed to assist in the process of choosing travel destinations and planning tourist trips (see an overview in Section 2). Considering that Tourism is an activity strongly connected to personal preferences and interests (Garcia, Sebastia, & Onaindia, 2011), recommender systems usually rely on ratings and opinions of previous users to suggest possible destinations.

As will be shown in the related work section, most of the recommender systems that have been developed in the last years focus on the analysis and comparison of tourist destinations, to help the user to select the most appropriate one. However, it is also of great importance for the user to be aware of the specific attractions that can be visited when he/she has already arrived at a particular destination. Information about points of interest and cultural and leisure activities is very dynamic and, in many cases, difficult to retrieve, analyse and filter. On-site dynamic recommendations play an important role both for the tourist, who is interested in attractions that he/she may enjoy according to his/her personal profile, and for the destination provider, who is interested in increasing the visibility of the available attractions, especially in the case of low-profile activities in popular destinations, an important aspect of the so called sustainable Tourism (Borrás et al., 2011). In recent years, a scarce number of tourism recommender systems have focused on this aspect. Unlike the above-mentioned systems, these approaches should face, in addition to the profile-based recommendation task, other related issues such as the retrieval and appropriate consideration of the user’s constraints during the stay (e.g., in aspects like budget, accessibility, language or agenda), the dynamic determination of the user’s position and its integration in a location-aware recommendation process (i.e., geo-localisation of the user and the points of interest), and the inclusion of a desirable high degree of proactivity and dynamicity in order to adapt the system’s suggestions to the behaviour of the user at the destination (Castillo et al., 2008).

The system presented in this paper is framed in this context and it has been designed with the following main goals in mind: (i) to provide an easy and ubiquitous access to the desired information about tourist attractions, (ii) to provide proactive recommendations of attractions by means of a hybrid recommendation system that considers elements such as the user profile and preferences, the location of the tourist and the activities, and the opinions of previous tourists, and (iii) to implement a high degree of dynamicity and flexibility so that the system can easily adapt to changes in the activities and incorporate new information transparently at execution time.

From a technological perspective, the system relies on agent technology to provide a solution fitting with the above-mentioned goals. Agents and multi-agent systems (Wooldridge, 2009) allow modelling, at a very high level, heterogeneous and distributed systems and environments, and can act autonomously and proactively while cooperating between them to solve a complex problem (Isern, Sánchez, & Moreno, 2011; Isern et al., 2011). Agent-based systems offer added values thanks to features not found in classical software engineering paradigms such as elaborated communicative skills, which allow complex negotiation processes, and a high degree of flexibility and modularity (Moreno, Isern, & Sánchez, 2003; Sánchez, Isern, Rodríguez-Rozas, & Moreno, 2011).

Summarising, this paper presents an agent-based recommender system called Turist@. The tourist interacts through a graphical interface with a User Agent that may be running in the user’s mobile phone or PDA. There is a Recommender Agent that stores the preferences of each user. These preferences are initialised with a brief questionnaire, but are continuously refined and updated through the analysis of the actions made by the user in the system (e.g., the queries he/she makes, or the evaluations performed after visiting a particular attraction). Thus, a combination of explicit and implicit techniques is considered to manage the user profile. The system provides proactive location-based recommendations, warning the user when it is near an activity that may be interesting for him/her. The items to be recommended are computed with a mixture of content-based and collaborative techniques.

The rest of the paper is organised as follows. Section 2 discusses related works proposing recommenders systems focused on the Tourism field. Section 3 explains the design and architecture of the proposed solution, based on a multi-agent system. Section 4 describes the management and update of user profiles. Section 5 describes the different strategies and methods used to implement the recommendation process according to the user’s preferences. The final section discusses and summarises the main contributions of the work.