Biomedical Engineering Reference
In-Depth Information
The most promising approaches to text mining online documents rely on natural language processing
(NLP), a technology that encompasses a variety of computational methods ranging from simple
keyword extraction to semantic analysis (see
Figure 7-15
). The simplest NLP systems work by
parsing documents and identifying the documents with recognized keywords such as "protein" or
"amino acid." The contents of the tagged documents can then be copied to a local database and later
reviewed.
Figure 7-15. Text Mining with NLP. Simple keyword extraction is useful in
identifying documents, analysis of keyword distribution identifies document
clusters, and semantic analysis can reveal rules and trends.
More elaborate NLP systems use statistical methods to recognize not only relevant keywords, but
their distribution within a document. In this way, it's possible to infer context. For example, an NLP
system can identify documents with the keywords "amino acid", "neurofibromatosis", and "clinical
outcome" in the same paragraph. The result of this more advanced analysis is document clusters,
each of which represents data on a specific topic in a particular context.
This capability of identifying documents or document clusters is used by the typical Web search
engines, such as Google or Yahoo!, or the native PubMed interface. This approach is also used in
commercial bibliographic database systems, such as EndNote
®
, ProCite
®
, and Reference Manager
®
,
