During the last decade a lot of academic papers consider the possibility of predicting the economic fluctuations and macroeconomic variables volatility with the use of news data. The reason for this is the development of new machine learning techniques and enhancement of the existed methods. The scientific problem of our study is the investigation of whether predictive power of the forecast of macroeconomic variables can be improved with the use of news data in the context of Russia. We apply NLU algorithms and techniques for topic modeling. Especially, we implement LDA (Latent Dirichlet Allocation) since this approach has shown its effectiveness in the published papers related to the mentioned framework. Then the frequency news and sentiment news indexes are constructed with the use of modeled topics. The end point of our research is the forecast analysis of the set of macroeconomics variables [CPI (π), Business Confidence Index (BCI), Consumer Confidence Index (CCI), Export (EX), Import (IM), Net Export (NX)] supplemented by inclusion of frequency and sentiment news indexes in order to evaluated the improvement in predictive power. We have shown that the inclusion of frequency news indexes and sentiment news indexes, based on the LDA approach in the forecast models can improve the quality of the predictions and increase the predictive power for some variables.