Gender Factor in Associative Links of Words: Dictionary and Distributive-Semantic Model Data

The aim of the work is to make a comparative analysis associative links full-meaning words from upper zone frequency list, compiled on basis research corpus blog texts in Russian, psycholinguistic experiment and distributivesemantic model Global Vectors (GloVe), trained this corpus. relevance due need for comprehensive study psychologically relevant meaning word. novelty lies fact that such an carried out taking into account gender factor respondent / author text. use set methods data mining (clustering, classification) visualization its results made it possible establish influence composition semantic associates analyzed (that is, with close vectors distributive-semantic model) absence effect their recorded dictionary. As showed, models dictionary norms reflect different aspects content word should be used as complementary sources when modeling word, individual characteristics speaker, while conducting advisable methods.