Literature-Based Discovery: Critical Analysis and Future Directions

Literature-Based Discovery (LBD) is the science of relating existing knowledge in literature to discover new relationships. It is sometimes referred to as hidden knowledge. The paper provides the most recent classification of the existing LBD methods relating the problem to other domains such as information retrieval. The paper identifies that Vector Space Model, Probabilistic Model, and Inference Network Model are the mostly used for LBD problem. The researchers of this paper justified their belief that there are important differences between the two problem domains with regards to novelty, time factor, reasoning, and relevance. The paper investigates the hypothesis that some discoveries could have been materialised earlier based on some early relatedness indicators. The latter point is an interesting one that offers some direction for the future research in LBD. Moreover, the paper introduces the ongoing work of the author on proposing a new evaluation methodology that addresses the weaknesses of the current methodologies investigating the desirable characteristics of the future LBD evaluation methodology.