Tourism Recommender System Research Articles

Parallel context-aware multi-agent tourism recommender system

The presence of millions and millions of users and items makes real time filtering a time consuming process in recommender systems (RS). In context aware recommender systems (CARS), choices of users depend on the contextual information as well as available items. The rapid change in interests of a user under different contexts puts extra load on RS. To address this problem, we present a parallel approach for CARS using a multi-agent system which accelerates the processing time drastically using General Purpose Graphic Processing Unit (GPGPU). Contextual pre-filtering and multi-agent environment update the system with the user context. A prototype of the system is developed using JCuda, JADE and Java technologies for tourism domain. The performance of the presented system is compared with the CARS without parallel processing with respect to processing time, scalability as well as precision, recall and F-measure. The results show a significant speedup for presented system over non-parallel CARS.

Survey on Customized Tourism and Travel Recommendation System based on User-location Vector Approach

Survey on Customized Tourism and Travel Recommendation System based on User-location Vector Approach

Using POI functionality and accessibility levels for delivering personalized tourism recommendations

The aim of this paper is to propose a recommendation system that considers user's functionality levels regarding physical or psychological limitations. This paper describes a set of models and algorithms used under a tourism recommendation system based in users and points-of-interest (POI) profiles. Also, this proposal considers a different manner to classify POI including their accessibility levels, mapped with similar physical and psychological issues. In this study, based on the Design Science Research methodology, an architecture is proposed and a touristic recommendation system prototype where users are modelled with new types of information in addition to traditional approaches such as their levels of functionality regarding a set of physical and intellectual issues, is also presented. POIs are also modelled with the same information structure and maintain knowledge on their limitations against some health conditions.

Social Trust Based Semantic Tourism Recommender System: A Case of Medical Tourism in Tunisia

Based on the assumption that users generally have a tendency to use items recommended by friends rather than strangers and that trust among friends positively correlates with user preference, we decided to refer to research conducted on the emerging field of trust-based recommender system. We propose to integrate the temporal factor in measuring trust between social network friends. A Trusted Friend’s calculation method is developed for determining social trusted friends in Facebook. We have, accordingly, demonstrated the importance of the interactions’ time between users. Afterwards, we have used this method in a semantic tourism recommender system as a smart e-tourism tool able to recommend items based on the users’ preferences and their trusted friends’ preferences. We have also applied our tourism recommender system for the case of medical tourism in Tunisia to help users interested in traveling to Tunisia for medical purposes. Finally, we have implemented the system and collected feedback from real users to evaluate the quality of recommendation and prove its importance in improving the medical tourism domain.

A CONTEXT-AWARE TOURISM RECOMMENDER SYSTEM BASED ON A SPREADING ACTIVATION METHOD

Abstract. Users planning a trip to a given destination often search for the most appropriate points of interest location, this being a non-straightforward task as the range of information available is very large and not very well structured. The research presented by this paper introduces a context-aware tourism recommender system that overcomes the information overload problem by providing personalized recommendations based on the user’s preferences. It also incorporates contextual information to improve the recommendation process. As previous context-aware tourism recommender systems suffer from a lack of formal definition to represent contextual information and user’s preferences, the proposed system is enhanced using an ontology approach. We also apply a spreading activation technique to contextualize user preferences and learn the user profile dynamically according to the user’s feedback. The proposed method assigns more effect in the spreading process for nodes which their preference values are assigned directly by the user. The results show the overall performance of the proposed context-aware tourism recommender systems by an experimental application to the city of Tehran.

Using a four-step heuristic algorithm to design personalized day tour route within a tourist attraction

The design of personalized day-tour routes for tourists plays a fundamental role in improving tourists’ travel experiences, and it is a crucial practice for managers of tourist attractions in an increasingly competitive marketplace. This study constructs a tourist recommendation system with consideration for aesthetic fatigue and variable sightseeing value. A four-step heuristic algorithm (involving a genetic algorithm and a difference evolution algorithm) is proposed, which serves as the nucleus for a new system to deal with the tourist trip design problem. To evaluate the performance of this algorithm, a case study was conducted at the Jiuzhai Valley in Sichuan, China. The results of paired sample t-tests indicated that the proposed heuristic algorithm indeed performed significantly better than existing methods. Furthermore, the study showed that our proposed system was able to design more realistic and better personalized routes for tourists than previous systems.

Interval type-2 fuzzy Hamy mean operators and their application in multiple criteria decision making

Interval type-2 fuzzy set (IT2FS) is a widely used tool for handling vagueness and imprecision in real-world problems. To aggregate the interval type-2 fuzzy information, some useful aggregation operators have been developed such as IT2-OWA, IT2-FWA, and IT2-Frank operators. In particular, some aggregation operators which can capture and reflect and interrelationships among aggregated arguments are intensively studied, among which Hamy mean (HM) is an important alternative. However, the traditional HM does not focus on fusion of fuzzy information and the weighted vector of the aggregated arguments. In this study, we extend the HM to accommodate interval type-2 fuzzy environment and show its application to multiple criteria decision making (MADM). In order to simplify the computing, we first define the concept of symmetric triangular interval type-2 fuzzy set and propose some operational laws. Motivated by the idea of HM operator, we develop the symmetric triangular interval type-2 fuzzy Hamy mean (STIT2FHM) operator for aggregating the interval type-2 fuzzy information. Some useful properties such as monotonicity, boundedness, and idempotency are studied in detail. Furthermore, we discuss some special cases with respect to different parameter values of the STIT2FHM operator. For the situations where the input arguments have different importance, we further develop the weighted symmetric triangular interval type-2 fuzzy Hamy mean (WSTIT2FHM) operator to aggregate interval type-2 fuzzy information. Based on it, an approach to MCDM problems with symmetric triangular interval type-2 fuzzy information is developed. Finally, a real-world example concerning tourism recommender system is provided to illustrate the practicality and effectiveness of the proposed method.

A Japanese Tourism Recommender System with Automatic Generation of Seasonal Feature Vectors

Tourism recommender systems have been widely used in our daily life to recommend tourist spots to users meeting their preference. In this paper, we propose a contentbased tourism recommender system considering travel season of users. In order to characterize seasonal variable features of spots,the proposed system generates seasonal feature vectors in three steps: 1) to identify the vocabulary concerned through Wikipedia; 2) to identify the trend over all spots through Twitter for each season; and 3) to highlight the weight of words contained in each identified trend. In the decision of recommendation, it does not only match the user profile with features of spots but also takes user’s travel season into account. The effectiveness of the proposed system is evaluated by a series of experiments, i.e.computer simulation and questionnaire evaluation. The result indicates that: 1) those vectors certainly reflect the similarity of spots for designated time period, and 2) with using such vectors of spots, the system successfully realized a tourism seasonal recommendation.

Personalized Attraction Recommendation System for Tourists Through Check-In Data

Online social networks now play a prominent role in our daily lives and our decisions and behaviors in many areas. Of particular interest here is the application of social network data to give users access to tourist information. There is a growing need for information on tourism and tourist activities to satisfy user queries in this domain. Social networks, such as Facebook, Twitter, and Foursquare, among others, store substantial volumes of check-in data, which are a valuable resource for recommending tourism attractions. However, using Facebook check-in data has rarely been considered in conventional recommendation systems (RSs). This presents not only a new research challenge for the computer science and information technology fields but also an interesting opportunity for the tourism industry: knowing what kind of attractions tourists are interested in and how to acquire their user preferences without adding tasks to users of an RS. We propose a tourism RS that is based on its recommendations on data dynamically aggregated and extrapolated from the Facebook check-in data. In addition, the so-called “cold-start” problem has been resolved by using users’ Friends’ check-in data to analyze ongoing Facebook activity and update user profiles in the system. Most Facebook users have a well-extended list of Friends. Consequently, the proposed system can dynamically learn user behavior and appropriately adapt recommendations. This paper demonstrate the usefulness of the data available on Facebook through the example studies involving attraction recommendations, resolving the cold-start problem, and adapting the user model to improve recommendation quality in the tourism domain.

A Cold Start Context-Aware Recommender System for Tour Planning Using Artificial Neural Network and Case Based Reasoning

Nowadays, large amounts of tourism information and services are available over the Web. This makes it difficult for the user to search for some specific information such as selecting a tour in a given city as an ordered set of points of interest. Moreover, the user rarely knows all his needs upfront and his preferences may change during a recommendation process. The user may also have a limited number of initial ratings and most often the recommender system is likely to face the well-known cold start problem. The objective of the research presented in this paper is to introduce a hybrid interactive context-aware tourism recommender system that takes into account user’s feedbacks and additional contextual information. It offers personalized tours to the user based on his preferences thanks to the combination of a case based reasoning framework and an artificial neural network. The proposed method has been tried in the city of Tehran in Iran. The results show that the proposed method outperforms current artificial neural network methods and combinations of case based reasoning withk-nearest neighbor methods in terms of user effort, accuracy, and user satisfaction.

Parallel context-aware multi-agent tourism recommender system

The presence of millions and millions of users and items makes real time filtering a time consuming process in recommender systems (RS). In context aware recommender systems (CARS), choices of users depend on the contextual information as well as available items. The rapid change in interests of a user under different contexts puts extra load on RS. To address this problem, we present a parallel approach for CARS using a multi-agent system which accelerates the processing time drastically using General Purpose Graphic Processing Unit (GPGPU). Contextual pre-filtering and multi-agent environment update the system with the user context. A prototype of the system is developed using JCuda, JADE and Java technologies for tourism domain. The performance of the presented system is compared with the CARS without parallel processing with respect to processing time, scalability as well as precision, recall and F-measure. The results show a significant speedup for presented system over non-parallel CARS.

Efficient Image Geotagging Using Large Databases

There are now billions of images stored on photo sharing websites. These images contain visual cues that reflect the geographical location of where the photograph was taken (e.g., New York City). Linking visual features in images to physical locations has many potential applications, such as tourism recommendation systems. However, the size and nature of these databases pose great challenges. For example, the distribution of images around the world is highly biased towards popular regions. This results in high redundancy in certain locations, while under-representing the features in other regions. Many density estimation methods are unable to handle such datasets. In this paper we employ an on-line unsupervised clustering method, Location Aware Self-Organizing Map (LASOM), to compress a large image database and learn similarity relationships between different geographical locations. Our method achieves promising results when used on a dataset containing approximately 900,000 images. We further show that the learned representation results in minimal information loss as compared to using k-Nearest Neighbor method. The noise reduction property of LASOM allows for superior performance when combining multiple features. The final part of the paper explores clothing as a new information source that may assist in geolocation of images.

A Context-Awareness Personalized Tourist Attraction Recommendation Algorithm

AbstractWith the rapid development of social networks, location based social network gradually rises. In order to retrieve user’s most preferred attractions from a large number of tourism information, personalized recommendation algorithm based on the geographic location has been widely concerned in academic and industry. Aiming at the problem of low accuracy in personalized tourism recommendation system, this paper presents a personalized algorithm for tourist attraction recommendation – RecUFG Algorithm, which combines user collaborative filtering technology with friends trust relationships and geographic context. This algorithm fully exploits social relations and trust friendship between users, and by means of the geographic information between user and attraction location, recommends users most interesting attractions. Experimental results on real data sets demonstrate the feasibility and effectiveness of the algorithm. Compared with the existing recommendation algorithm, it has a higher prediction accuracy and customer satisfaction.

Planning for tourism routes using social networks

Traveling recommendation systems have become very popular applications for organizing and planning tourist trips. Among other challenges, these applications are faced with the task of maintaining updated information about popular tourist destinations, as well as providing useful tourist guides that meet the users preferences. In this work we present the PlanTour, a system that creates personalized tourist plans using the human-generated information gathered from the minube11www.minube.com traveling social network. The system follows an automated planning approach to generate a multiple-day plan with the most relevant points of interest of the city/region being visited. Particularly, the system collects information of users and points of interest from minube, groups these points with clustering techniques to split the problem into per-day sub-problems. Then, it uses an off-the-shelf domain-independent automated planner that finds good quality tourist plans. Unlike other tourist recommender systems, the PlanTour planner is able to organize relevant points of interest taking into account user’s expected drives, and user scores from a real social network. The paper also highlights how to use human provided recommendations to guide the search for solutions of combinatorial tasks. The resulting intelligent system opens new possibilities of combining human-generated knowledge with efficient automated techniques when solving hard computational tasks. From an engineering perspective we advocate for the use of declarative representations of problem solving tasks that have been shown to improve modeling and maintenance of intelligent systems.

Aggregating social media data with temporal and environmental context for recommendation in a mobile tour guide system

Purpose Manufacturers of smartphone devices are increasingly utilising a diverse range of sensors. This innovation has enabled developers to accurately determine a user’s current context. One area that has been significantly enhanced by the increased use of context in mobile applications is tourism. Traditionally, tour guide applications rely heavily on location and essentially ignore other types of context. This has led to problems of inappropriate suggestions and tourists experiencing information overload. These problems can be mitigated if appropriate personalisation and content filtering is performed. This research proposes an intelligent context-aware recommender system that aims to minimise the highlighted problems. Design/methodology/approach Intelligent reasoning was performed to determine the weight or importance of different types of environmental and temporal context. Environmental context such as the weather outside can have an impact on the suitability of tourist attractions. Temporal context can be the time of day or season; this is particularly important in tourism as it is largely a seasonal activity. Social context such as social media can potentially provide an indication of the “mood” of an attraction. These types of contexts are combined with location data and the context of the user to provide a more effective recommendation to tourists. The evaluation of the system is a user study that utilised both qualitative and quantitative methods, involving 40 participants of differing gender, age group, number of children and marital status. Findings This study revealed that the participants selected the context-based recommendation at a significantly higher level than either location-based recommendation or random recommendation. It was clear from analysing the questionnaire results that location is not the only influencing factor when deciding on a tourist attraction to visit. Research limitations/implications To effectively determine the success of the recommender system, various combinations of contextual conditions were simulated. Simulating contexts provided the ability to randomly assign different contextual conditions to ensure an effective recommendation under all circumstances. This is not a reflection of the “real world”, because in a “real world” field study the majority of the contextual conditions will be similar. For example, if a tourist visited numerous attractions in one day, then it is likely that the weather conditions would be the same for the majority of the day, especially in the summer season. Practical implications Utilising this type of recommender system would allow the tourists to “go their own way” rather than following a prescribed route. By using this system, tourists can co-create their own experience using both social media and mobile technology. This increases the need to retain user preferences and have it available for multiple destinations. The application will be able to learn further through multiple trips, and as a result, the personalisation aspect will be incrementally refined over time. This extensible aspect is increasingly important as personalisation is gradually more effective as more data is collated. Originality/value This paper contributes to the body of knowledge that currently exists regarding the study of utilising contextual conditions in mobile recommender systems. The novelty of the system proposed by this research is the combination of various types of temporal, environmental and personal context data to inform a recommendation in an extensible tourism application. Also, performing sentiment analysis on social media data has not previously been integrated into a tourist recommender system. The evaluation concludes that this research provides clear evidence for the benefits of combining social media data with environmental and temporal context to provide an effective recommendation.

Towards a social and context-aware mobile recommendation system for tourism

Loyalty in tourism is one of the main concerns for tourist organizations and researchers alike. Recently, technology in general and CRM and social networks in particular have been identified as important enablers for loyalty in tourism. This paper presents POST-VIA 360, a platform devoted to support the whole life-cycle of tourism loyalty after the first visit. The system is designed to collect data from the initial visit by means of pervasive approaches. Once data is analysed, POST-VIA 360 produces accurate after visit data and, once returned, is able to offer relevant recommendations based on positioning and bio-inspired recommender systems. To validate the system, a case study comparing recommendations from the POST-VIA 360 and a group of experts was conducted. Results show that the accuracy of system’s recommendations is remarkable compared to previous efforts in the field.

A secured context-aware tourism recommender system using artificial bee colony and simulated annealing

Context-aware recommender systems have been developed to consider users' preferences in various contextual situations. While designing such systems, one immediate concern, is to preserve the integrity of the recommender and minimise the attack probability of biased users who may indirectly influence the outcome of the system. Several algorithms have been developed to identify malicious users in contextual environments. In this paper, we propose a reputation-controlled fish school (RCFS) algorithm to identify trustable users and utilise them in recommendations. In addition, we propose a recommendation algorithm that replicates the behaviour of social insects using a hybrid artificial bee colony (ABC) and simulated annealing (SA) technique. Finally, we demonstrate that the resulting feedback strategies can increase the effectiveness of the recommenders' decisions.

An Agent Framework of Tourism Recommender System

This paper proposes the development of an Agent framework for tourism recommender system. The recommender system can be featured as an online web application which is capable of generating a personalized list of preference attractions for tourists. Traditional technologies of classical recommender system application domains, such as collaborative filtering, content-based filtering and content-based filtering are effectively adopted in the framework. In the framework they are constructed as Agents that can generate recommendations respectively. Recommender Agent can generate recommender information by integrating the recommendations of Content-based Agent, collaborative filtering-based Agent and constraint-based Agent. In order to make the performance more effective, linear combination method of data fusion is applied. User interface is provided by the tourist Agent in form of webpages and mobile app.

A Semantic Social Recommender System Using Ontologies Based Approach For Tunisian Tourism

Tunisia is well placed in terms of medical tourism and has highly qualified and specialized medical and surgical teams. Integrating social networks in Tunisian medical tourism recommender systems can result in much more accurate recommendations. That is to say, information, interests, and recommendations retrieved from social networks can improve the prediction accuracy. This paper aims to improve traditional recommender systems by incorporating information in social network; including user preferences and influences from social friends. Accordingly, a user interest ontology is developed to make personalized recommendations out of such information. In this paper, we present a semantic social recommender system employing a user interest ontology and a Tunisian Medical Tourism ontology. Our system can improve the quality of recommendation for Tunisian tourism domain. Finally, our social recommendation algorithm is implemented in order to be used in a Tunisia tourism Website to assist users interested in visiting Tunisia for medical purposes.

Building an Image Annotation and Tourism Recommender System

The interest in image annotation and recommendation has been increased due to the ever rising amount of data uploaded to the web. Despite the many efforts undertaken so far, accuracy or efficiency still remain open problems. Here, a complete image annotation and tourism recommender system is proposed. It is based on the probabilistic latent semantic analysis (PLSA) and hypergraph ranking, exploiting the visual attributes of the images and the semantic information found in image tags and geo-tags. In particular, semantic image annotation resorts to the PLSA, exploiting the textual information in image tags. It is further complemented by visual annotation based on visual image content classification. Tourist destinations, strongly related to a query image, are recommended using hypergraph ranking enhanced by enforcing group sparsity constraints. Experiments were conducted on a large image dataset of Greek sites collected from Flickr. The experimental results demonstrate the merits of the proposed model. Semantic image annotation by means of the PLSA has achieved an average precision of 92% at 10% recall. The accuracy of content-based image classification is 82, 6%. An average precision of 92% is measured at 1% recall for tourism recommendation.