Automatic diagnostics of manipulative mass media discourse (based on the corpus of Russian-language Internet publications)

Abstract

The article discusses the problem of manipulativeness of mass media discourse and its recognition using machine learning. The modern mass media discourse is addressed to the general reader, and can psychologically and informationally influence reader’s mood and behavior, forming certain beliefs, values, attitudes and worldview. Rapid development of information technologies and the daily replenishment of information Internet content significantly increases the risks and threat of such information impact. In this regard, the issues of studying the discourse of mass media, manipulation, and identifying features of manipulativeness of publications are relevant. The urgency is also emphasized by the acute need for a quick, automatic determination of published electronic text information that has a manipulative potential and is able to provide media manipulation of the mass consciousness. The phenomenon of the manipulative nature of mass media discourse is a complex occurrence that combines both linguistic and non-linguistic factors. Further computer diagnostics of the manipulativeness of publications using machine learning forms an understanding of the concept of manipulativeness, which highlights the linguistic representation of manipulative, “hidden” and obscured content, as well as understanding the homogeneity of the structure of manipulative text in the context of machine processing of large text arrays. For the first time, this manipulativeness concept helps to identify speech and language indicators of manipulativeness of Kazakhstani Russian-language Internet publications through linguistic and discourse analysis of 1000 publications provided by linguistic experts, selected from the corpus of 10,000 texts. The hypothesis of the research is that the identified indicators are valid metrics for the automatic diagnosis of electronic publications with manipulative potential, which are subjected to algorithmicizing for the subsequent machine processing.