Current recommender systems largely focus on static, unstructured content. In many scenarios, we would like to recommend content that has structure, such as a trajectory of points-of-interests in a city, or a playlist of songs. Dubbed Structured Recommendation, this problem differs from the typical structured prediction problem in that there are multiple correct answers for a given input. Motiv...

Many practical recommendation systems have been studied, and also the services based on such recommendation systems have been opened in real world. The main research questions of this work are i) how these recommendation services provide users with useful information, and ii) how different the results from the systems are from each other. In this paper, we propose a black-box evaluation framewo...

BACKGROUND Primary care providers (PCP) are the entry point for public sector depression treatment for many Latino patients. However, many Latino patients do not initiate their PCPs' recommended treatment, which likely contributes to ethnic disparities in depression treatment. This study examined factors related to Latino patients' uptake of their PCPs' recommendations for depression treatment....

Generating a useful recommendation is only the first step in creating a recommendation system. For the system to have value, the recommendations must be delivered with a user interface that allows the user to become aware that recommendations are available, to determine if any of the recommendations have value for them and to be able to act upon a recommendation. By synthesizing previous result...

Collaborative filtering recommender technology is also known as user-oriented recommendation techniques, is currently the most successful personalized recommendation. This paper describes the collaborative filtering recommendation techniques, collaborative filtering recommendation of three steps, and generation of a neighbor recommended. The traditional collaborative filtering algorithm has bee...

The role of context in our daily interaction with our environment has been studied in psychology, linguistics, artificial intelligence, information retrieval, and more recently, in pervasive/ubiquitous computing. However, context has been largely ignored in research into recommender systems specifically and personalization in general. In this paper we describe how context can be brought to bear...

Personalized recommendation is well researched area, but the group recommendation still needs to be explored. In this paper we propose an idea of approach for the single user recommendation based on the principles of the group recommendation. We explore several setting of such an approach in order to the group size or the number of similar users used for the recommendation. Experiments are perf...

In view of the issue of internal data in the construction of recommendation system may be leaked by external person. A privacy-preserving recommendation system based on MASK is designed to address it. The system consists of two parts: privacy-preserving subsystem and recommendation subsystem. First, disrupt original data to form new privacy-preserving data according to a certain probability. Se...

This paper analyzes influential factors of recommendation behaviour in social network sites (SNSs). Extant research on both SNSs and electronic word of mouth (eWOM) has given insufficient attention to SNSs as a potential eWOM channel. Considering the specificities of SNSs, this paper distinguishes implicit and explicit recommendation behaviour. Drawing upon research on eWOM, SNSs, and knowledge...