The research paper focuses on the mechanism of semantic parser for automatic text analysis and represents some results of analyzing news with a total volume of 2.2 million clauses. This mechanism models the processes of text comprehension and in this paper it is applied to the evaluation of the text influence on the reader. The parser constructs a semantic representation of the text and maps the meaning of each clause to a particular frame belonging either to the set of 300 emotional or to the set of 4500 rational frames. Comparing the frames of pro-state (federal) and blocked sources in Russia, the authors show that the most frequent frames in federal news represent an interactive dialog between the media and the speaker (note, add, recall, etc.), while the most frequent frames in blocked news introduce the speaker’s utterance that has become known to the news agencies (report, write, say, etc.). This reflects the remoteness of the editors of blocked news from Russian speakers. The federal media more often report about funny or unexpected purchases, as well as about how federal employees rescue people, and this agenda should make a positive impression. The blocked media, on the other hand, are more likely to mention court sentencing and death, which should have a negative impact. The natural-language inference constructed via frame combinations is shown to enable the recognition of emotional situations in derived meanings that are not explicitly expressed in the text and, thus, it allows to analyze automatically more compound mechanisms of manipulation.