Analysis of Semantic Relatedness of Terms in Uzbek Electronic Corpus

When converting textual data into a vector representation and analyzing their semantics using vectorized form of texts, it is necessary to take into account the semantic relations between concepts. There are not always enough resources that explores the relations such as synonymy, homonymy, and antonymy between concepts. In addition, there are relations of semantic connectedness, which can be analyzed only through the language corpus. This article considers the issue of determining the relations of semantic connectedness between concepts by means of frequency analysis of texts using a dictionary. It is intended to use the bigram model in the implementation of frequency analysis. In addition, authors organized quite deep research in comparative analysis of existing works by showing their advantages and drawbacks. Besides, thanks to this analysis it might be seen that there is a big actuality of the current work. In addition, the authors plan to implement more advanced algorithms in the future that are capable of identifying semantic links with a wider thematic set.