A semantic approach to involve Twitter in LBD efforts

Literature-based Discovery (LBD) refers to the task of finding hidden, unknown or neglected relationships that may be uncovered using biomedical text. While traditional LBD primarily focuses on MEDLINE records for unearthing such relationships, recent studies have shown the applicability of contemporary textual resources such as electronic medical records or online medical message boards for similar purposes. In this paper we highlight yet another source for LBD, i.e., Twitter data. We focus on the use of Twitter as a new resource for finding hypotheses - both novel and slightly studied. Using a set of drug and disease names as starting points we retrieve thousands of Twitter messages which are then processed for semantic information to mine several hundred biomedical relationships which we call probes. Manual inspection of a handful of these probes reveals instances where tweets strongly support a hypothesis for which no evidence can be found in PubMed. In other cases, we find very few related PubMed records supporting/rejecting such Twitter-mined probes. Overall, we show the importance and usefulness of Twitter for LBD efforts.