Title | ||
---|---|---|
Text Mining approaches for automated literature knowledge extraction and representation. |
Abstract | ||
---|---|---|
Due to the overwhelming volume of published scientific papers, information tools for automated literature analysis are essential to support current biomedical research. We have developed a knowledge extraction tool to help researcher in discovering useful information which can support their reasoning process. The tool is composed of a search engine based on Text Mining and Natural Language Processing techniques, and an analysis module which process the search results in order to build annotation similarity networks. We tested our approach on the available knowledge about the genetic mechanism of cardiac diseases, where the target is to find both known and possible hypothetical relations between specific candidate genes and the trait of interest. We show that the system i) is able to effectively retrieve medical concepts and genes and ii) plays a relevant role assisting researchers in the formulation and evaluation of novel literature-based hypotheses. |
Year | DOI | Venue |
---|---|---|
2010 | 10.3233/978-1-60750-588-4-954 | Studies in Health Technology and Informatics |
Keywords | Field | DocType |
Text Mining,Annotation networks,Gene ranking,Candidate gene study | Text graph,Data mining,Concept mining,Text mining,Search engine,Annotation,Information retrieval,Biomedical text mining,Gene ranking,Knowledge extraction,Medicine | Conference |
Volume | Issue | ISSN |
160 | Pt 2 | 0926-9630 |
Citations | PageRank | References |
4 | 0.43 | 6 |
Authors | ||
7 |
Name | Order | Citations | PageRank |
---|---|---|---|
Angelo Nuzzo | 1 | 61 | 6.15 |
Francesca Mulas | 2 | 4 | 0.43 |
Matteo Gabetta | 3 | 12 | 3.39 |
Eloisa Arbustini | 4 | 5 | 1.49 |
Blaz Zupan | 5 | 16 | 1.80 |
Cristiana Larizza | 6 | 4 | 0.77 |
Riccardo Bellazzi | 7 | 5 | 1.59 |