Publishing data as Linked Data increases the interoperability and discoverability of resources over the web space. This process involves several design decisions and technologies. However, there is no one-size-fits-all formula for publishing data as Linked Data. Also, the quality of linked data published is a key issue to take into account. In the library domain, the quality of linked data is a crucial point for improving the retrieval and use of the data. In this paper, we propose a set of methodological guidelines based on five activities for publishing library data as Linked Data. The proposed guidelines consider the quality of published data as a key issue. In this line, our approach includes a preprocessing task for data cleansing and normalization. The proposed approach has been applied in a use case for publishing bibliographic data from Open Access journals in Cuba. The results obtained show the applicability of the methodological guidelines proposed in a real environment.