Web directories organize voluminous information into hierarchical structures, helping users to quickly locate relevant information and to support decision-making. The development of existing Web directories either relies on expert participation that may not be available or uses automatic approaches that lack precision. As more users access the Web in their native languages, better approaches to organizing and developing non-English Web directories are needed. In this paper, we have proposed a semi-automatic approach to building domain-specific Web directories in different languages by combining human precision and machine efficiency. Using the approach, we have built Web directories in the Spanish business (SBiz) and Arabic medical (AMed) domains. Experimental results show that the SBiz and AMed directories achieved significantly better recall, F value, and satisfaction rating than benchmark directories. These encouraging results show that the approach can be used to build high-quality Web directories to support decision-making.