Abstract
Sentiment lexicons play an important role in opinion mining systems and cognitive linguistics. Previous work aimed mostly at creating sentiment lexicons, but not thorough research into their fundamental properties. In this paper, we study the arrangement of sentiment lexica in the multidimensional space of distributed word representations. We introduce a hypothesis on the existence of sentiment lexica concentration areas and test it on the basis of the joint analysis of the distribution of sentiment words and general lexica. The results of the test allow us to confirm the proposed hypothesis and discover the words which more than 80% of the sentiment lexica is concentrated around.