Even though search systems are very efficient in retrieving world-wide information, they cannot capture some peculiar aspects of user needs, such as subjective opinions, or information that require local or domain specific expertise. In these scenarios the knowledge of an expert or a friend’s advice can be more useful than any information retrieved by a search system. This way of exploiting human knowledge for information seeking and computational task is called Crowdsourcing. The main objective of this work is to develop methodologies for the creation of applications based on Crowdsourcing and social interaction. The outcome will be a framework based on model-driven approach that will allow end user to develop their own application with a fraction of the effort required by the traditional approaches. It will guarantee a strong control of the execution of the crowdsourcing task by mean of a declarative specification of objectives and quality measures. A prototype will be developed that will allow the creation and execution of task on various platforms. Validation of the approach will consist of quantitative and qualitative analysis of results and performance of the system upon some sample scenarios, where real users from social networks and crowdsourcing platforms will be involved.