Institutional Repository [SANDBOX]
Technical University of Crete
EN  |  EL

Search

Browse

My Space

Automatic document categorisation by user profile in medline

Petrakis Evripidis, Chliaoutakis Angelos

Full record


URI: http://purl.tuc.gr/dl/dias/9B89D963-866F-47ED-A380-D69B9441F9CD
Year 2011
Type of Item Conference Paper Abstract
License
Details
Bibliographic Citation Angelos Hliaoutakis, Euripides G.M.Petrakis. (2011, Sep.). Automatic Document Categorization by User Profile in Medline. Presented at 15th International Symposium on Health Information Management Research (ISHIMR'2011).[Online]. Available: http://www.intelligence.tuc.gr/~petrakis/publications/ISHIMR2011.pdf
Appears in Collections

Summary

We investigate potential improvements to the problem of term extraction related to document representation and indexing in large document collections such as Medline, the premier bibliographic database of the U.S. National Library of Medicine (NLM). Using term extraction methods such as AMTEX and MMTX, document representations are semantically compact and more efficient, being reduced to a limited number of meaningful multi-word terms (phrases), rather than large vectors of single-words, part of which may be void of distinctive content semantics. We show how this information can be used for the automatic categorisation of medical documents by user profile (i.e., novice users and experts). This is achieved by mapping document terms to external lexical resources such as WordNet, and MeSH (the medical thesaurus of NLM). Evaluation results of all methods are presented and discussed.

Services

Statistics