Dissertation Information for Meliha Yetisgen YildizNAME:
DEGREE:
DISCIPLINE:
SCHOOL: ADVISORS: COMMITTEE MEMBERS: MPACT Status: Fully Complete Title: Using statistical and knowledge-based approaches for literature-based discovery Abstract: Information overload has become a significant problem for biomedical researchers. While researchers formulate new hypotheses to test, it is very important for them to follow new findings and identify connections to their work from other parts of the literature. Scientific literature is readily available, but the sheer volume and growth rate of the literature makes it impossible for researchers to keep up with new findings outside their own narrowing fields of expertise. This isolation of researchers inhibits innovation across multiple fields. To solve this problem, I developed a system called LitLinker to help researchers identify new knowledge that bridges gaps across distinct sections of literature. LitLinker incorporates literature-based discovery (LBD), knowledge-based methodologies, statistical methods and information extraction approaches to mine the biomedical literature for new, potentially causal connections between biomedical terms. In this dissertation, I describe the design details of LitLinker. I also propose an evaluation methodology for LBD systems that allows comparisons across different systems and use it to compare the performance of various methods used by LitLinker and the other existing LBD systems. |
MPACT Scores for Meliha Yetisgen YildizA = 0 Advisors and Advisees Graph |