Transitive Text Mining for Information Extraction and Hypothesis Generation

Transitive text mining - also named Swanson Linking (SL) after its primary and principal researcher - tries to establish meaningful links between literature sets which are virtually disjoint in the sense that each does not mention the main concept of the other. If successful, SL may give rise to the development of new hypotheses. In this communication we describe our approach to transitive text mining which employs co-occurrence analysis of the medical subject headings (MeSH), the descriptors assigned to papers indexed in PubMed. In addition, we will outline the current state of our web-based information system which will enable our users to perform literature-driven hypothesis building on their own.