Big data in tourism research: A literature review

A recommender system (RS) aims to provide personalized recommendations to users for specific items (e.g., music, books). Popular techniques involve content-based (CB) models and collaborative filtering (CF) approaches. In this paper, we deal with a very important problem in RSs: The cold start problem. This problem is related to recommendations for novel users or new items. In case of new users, the system does not have information about their preferences in order to make recommendations. We propose a model where widely known classification algorithms in combination with similarity techniques and prediction mechanisms provide the necessary means for retrieving recommendations. The proposed approach incorporates classification methods in a pure CF system while the use of demographic data help for the identification of other users with similar behavior. Our experiments show the performance of the proposed system through a large number of experiments. We adopt the widely known dataset provided by the GroupLens research group. We reveal the advantages of the proposed solution by providing satisfactory numerical results in different experimental scenarios.

Facing the cold start problem in recommender systems

What makes a good recommendation or good list of recommendations?Research into recommender systems has traditionally focused on accuracy, in particular how closely the recommender’s predicted ratings are to the users’ true ratings. However, it has been recognized that other recommendation qualities—such as whether the list of recommendations is diverse and whether it contains novel items—may have a significant impact on the overall quality of a recommender system. Consequently, in recent years, the focus of recommender systems research has shifted to include a wider range of “beyond accuracy” objectives.In this article, we present a survey of the most discussed beyond-accuracy objectives in recommender systems research: diversity, serendipity, novelty, and coverage. We review the definitions of these objectives and corresponding metrics found in the literature. We also review works that propose optimization strategies for these beyond-accuracy objectives. Since the majority of works focus on one specific objective, we find that it is not clear how the different objectives relate to each other.Hence, we conduct a set of offline experiments aimed at comparing the performance of different optimization approaches with a view to seeing how they affect objectives other than the ones they are optimizing. We use a set of state-of-the-art recommendation algorithms optimized for recall along with a number of reranking strategies for optimizing the diversity, novelty, and serendipity of the generated recommendations. For each reranking strategy, we measure the effects on the other beyond-accuracy objectives and demonstrate important insights into the correlations between the discussed objectives. For instance, we find that rating-based diversity is positively correlated with novelty, and we demonstrate the positive influence of novelty on recommendation coverage.

Diversity, Serendipity, Novelty, and Coverage: A Survey and Empirical Analysis of Beyond-Accuracy Objectives in Recommender Systems

Novelty and diversity have been identified, along with accuracy, as foremost properties of useful recommendations. Considerable progress has been made in the field in terms of the definition of methods to enhance such properties, as well as methodologies and metrics to assess how well such methods work. In this chapter we give an overview of the main contributions to this area in the field of recommender systems, and seek to relate them together in a unified view, analyzing the common elements underneath the different forms under which novelty and diversity have been addressed, and identifying connections to closely related work on diversity in other fields.

Novelty and Diversity in Recommender Systems

A big data analytics method for tourist behaviour analysis

A nursing activity recognition method from nurses' interactions with the tools and materials he/she touched has been developed for preventing the cause of medical accidents and incidents. The method detects an interaction between a nurse and a tool or material by using a RFID tag system. From interaction data, activities are recognized by using the Dynamic Bayesian Network (DBN) framework. This paper focuses on recognizing the twelve activity steps in the drip injection task. In an experiment, we obtained the 95.4% accuracy in recognizing these steps.

Activity recognition from interactions with objects using dynamic Bayesian network

Recent work has focused on new measures that are beyond the accuracy of recommender systems. Serendipity, which is one of these measures, is defined as a measure that indicates how the recommender system can find unexpected and useful items for users. In this paper, we propose a Fusion-based Recommender System that aims to improve the serendipity of recommender systems. The system is based on the novel notion that the system finds new items, which have the mixed features of two user-input items, produced by mixing the two items together. The system consists of item-fusion methods and scoring methods. The item-fusion methods generate a recommendation list based on mixed features of two user-input items. Scoring methods are used to rank the recommendation list. This paper describes these methods and gives experimental results.

Fusion-based Recommender System for Improving Serendipity.

In this paper, a concept of â€œsymbiotic computingâ€ is formalized to bridge gaps between Real Space (RS) and Digital Space (DS). Symbiotic computing is a post-ubiquitous computing model based on an agent-oriented computing model that introduces social heuristics and cognitive functions into DS to bridge the gaps. The symbiotic functions and agent-based architecture of symbiotic applications are also discussed. Based on the concept, functions, and architecture of symbiotic applications, we develop an agent-based care-support service to enable supervision of persons by their families and friends easily while protecting privacy. In this application system, a hierarchical structure of multi-agents is organized dynamically using heuristics in agents based on the situation of a watched person and watching persons. The system appropriately alters the contents and quality of the live video. The flexible system construction scheme using a multiagent framework facilitates the symbiosis of RS and DS by bridging the gaps in the care-support service domain.

Concept of symbiotic computing and its agent-based application to a ubiquitous care-support service

Dementia occurs in every country of the world, especially in developed nations. Since such spatially and cognitive impaired people lack the ability to grasp positional relationship between landmarks, we have developed a walk navigation system using photographs of landmarks to benefit them and their families. Our system provides a photograph of the next target landmark to the mobile devices of cognitive impaired people. It can also identify points where cognitive impaired are likely to get lost. Our system can also support such tasks as taking tickets by photographs and animations.

/pdf/walk-navigation-system-using-photographs-for-people-with-rqs7md3yo9.pdf

Walk navigation system using photographs for people with dementia

CARS-2010 : 2nd Workshop on Context-Aware Recommender Systems , September 26, 2010, Barcelona, Spain

/pdf/a-recommendation-system-considering-users-past-current-3vvdcx0ssp.pdf

Fumio Hattori

Papers

Activity recognition from interactions with objects using dynamic Bayesian network

Fusion-based Recommender System for Improving Serendipity.

Concept of symbiotic computing and its agent-based application to a ubiquitous care-support service

Walk navigation system using photographs for people with dementia

A Recommendation System Considering Users' Past / Current / Future Contexts