Recently, there has been a burgeoning interest in keyword search in relational databases owing to its ease of use. Although extensive research has been lately done within this context, most of this research not only requires a prior access to data which severely restricts their applicability if this condition is not verified, but also returns very generic answers. However, providing users with personalized answers has become more than ever necessary due to the overabundance of data which can be annoying for the user. The challenge to return personalized and relevant answers that satisfy users' information needs remains. Inspired by the successful application of the collaborative filtering technique in recommender systems, we propose a novel keyword-based approach to provide users with personalized results based on the hypothesis that only information on the database schema is available.