Literature-based discovery systems aim at discovering valuable latent connectionsbetween previously disparate research areas. This is achieved by analyzing thecontents of their respective literatures with the help of various intelligentcomputational techniques. In this paper, we review the progress ofliterature-based discovery research, focusing on understanding their technicalfeatures and evaluating their performance. The present literature-baseddiscovery techniques can be divided into two general approaches: the traditionalapproach and the emerging approach. The traditional approach, which dominate thecurrent research landscape, comprises mainly of techniques that rely onutilizing lexical statistics, knowledge-based and visualization methods in orderto address literature-based discovery problems. On the other hand, we have alsoobserved the births of new trends and unprecedented paradigm shifts among therecently emerging literature-based discovery approach. These trends are likelyto shape the future trajectory of the next generation literature-based discoverysystems.
