Abstract:
The article describes the method of calculating the coefficients of semantic
proximity between scientific articles based on the use of semantic analysis
of the text elements, as well as analysis of the structural elements of a
scientific article. The scientific article is presented as a fuzzy set whose
elements are the terms where each term is assigned a grade of membership,
which characterizes the degree of its importance for this document. The
described technique offers a new way to calculate the weight coefficients of
the terms in the text. It also introduces a metric measuring the distance
between scientific articles, which takes into account implicit semantic
links between the compared documents. To obtain semantic characteristics of
the terms in the study Wiktionary is used as a thesaurus.
Keywords:semantic analysis, a measure of proximity documents Wiktionary, the semantic net of a document, fuzzy sets.
Fulltext:
PDF file (643 kB)