The development of internet engendred an important proliferation of items. Thus, users are often overwhelmed and unable to detect the items corresponding to their needs. Therefore, the need of tools for automatic personalization of information becomes heightened. Recommender systems are widely used for this purpose thanks to their ability to guide users towards relevant items. Despite the success of recommender systems in many application areas, some research questions still remain. Some of these questions concern sparsity, selection of reliable neighbors, precision of recommendations and cold start problem. In this PhD thesis we explored these issues and proposed some solutions. We suggested a new approach inspired from web usage mining an...
International audienceRecommender systems aim at suggesting items to users that fit their preference...
Internet constitutes an unstructured, almost infinite, and evolutive environment supplying heterogen...
Internet constitutes an unstructured, almost infinite, and evolutive environment supplying heterogen...
The development of internet engendred an important proliferation of items. Thus, users are often ove...
Face to the ongoing rapid expansion of the Internet, user requires help to access to items that may ...
Face to the ongoing rapid expansion of the Internet, user requires help to access to items that may ...
This work tackles different aspects of how to predict users' interest and behavior with social netwo...
In this thesis, we address the scalability problem of recommender systems. We propose accu rate and ...
Recommender Systems aim at pre-selecting and presenting first the information in which users may be ...
In this thesis, we address the scalability problem of recommender systems. We propose accu rate and ...
Recommender systems are widely used to achieve a constantly growing variety of services. Alongside w...
In this thesis we propose semantic-social recommendation algorithms, that recommend an input item to...
Recommender systems are widely used to achieve a constantly growing variety of services. Alongside w...
Among machine learning systems, recommendation engines hold a place of special relevance to industry...
International audienceThe exponential evolution of information on theWeb and information retrieval s...
International audienceRecommender systems aim at suggesting items to users that fit their preference...
Internet constitutes an unstructured, almost infinite, and evolutive environment supplying heterogen...
Internet constitutes an unstructured, almost infinite, and evolutive environment supplying heterogen...
The development of internet engendred an important proliferation of items. Thus, users are often ove...
Face to the ongoing rapid expansion of the Internet, user requires help to access to items that may ...
Face to the ongoing rapid expansion of the Internet, user requires help to access to items that may ...
This work tackles different aspects of how to predict users' interest and behavior with social netwo...
In this thesis, we address the scalability problem of recommender systems. We propose accu rate and ...
Recommender Systems aim at pre-selecting and presenting first the information in which users may be ...
In this thesis, we address the scalability problem of recommender systems. We propose accu rate and ...
Recommender systems are widely used to achieve a constantly growing variety of services. Alongside w...
In this thesis we propose semantic-social recommendation algorithms, that recommend an input item to...
Recommender systems are widely used to achieve a constantly growing variety of services. Alongside w...
Among machine learning systems, recommendation engines hold a place of special relevance to industry...
International audienceThe exponential evolution of information on theWeb and information retrieval s...
International audienceRecommender systems aim at suggesting items to users that fit their preference...
Internet constitutes an unstructured, almost infinite, and evolutive environment supplying heterogen...
Internet constitutes an unstructured, almost infinite, and evolutive environment supplying heterogen...