Workers in online crowd sourcing systems have different levels of expertise, trustworthiness, incentives and motivations. Therefore, recruiting sufficient number of well-suited workers is always a challenge. Existing methods usually recruit workers through open calls, friendships relations, matching their profiles with task requirements or recruiting teams of workers. But there are still challenges that need more investigations, mainly all existing recruitment methods are highly vulnerable to collaborating misbehaviour, i.e., Collusion. %These groups are highly vulnerable to collusion attacks. In this paper, we propose a recruitment method which takes into account individual and social attributes of workers to find suitable workers. The method discovers indirect collaborations between workers to harness implicit teamwork knowledge in order to increase the quality of crowd sourcing tasks' outcome and in the same time prevent collusion attacks. The proposed method is implemented and tested using the simulated data, build based on a public data dump from Stack overflow. The evaluation results show the accuracy of the obtained results and superiority of our proposed method over the other related work.