Our goal is to develop an automated model for successful reading, assuming the ability to select the perfect text for any reader.

To achieve the set goal, NIL ITUT plans to perform the following tasks:

1. To identify a set of the most informative metrics for evaluating the difficulty of Russian text.
2. To create an automatic text complexity analyzer.
3. To create a corpus of ranked texts aimed for at different categories of readers.
4. To simulate the perception features of different types of texts by different categories of readers.
5. To suggest and test reading training strategies for different categories of readers (2022).
6. Develop and implement an interactive model for teaching reading strategies (2022–2025).

Relevance

Today’s world challenges a person to quickly and fully extract information from printed text. Along with the increasingly complex world a text itself becomes more and more complex; a reader does not have time to carefully study a text in detail. This may cause misunderstanding or incomplete understanding of a text, which entails conflicts, mistakes, accidents, and tragedies.

Thus, the relevance of this academic field is determined by the following factors: 1. a lack of a list of parameters determining the correlation between 'reader and text'; 2. the importance of developing and implementing the systems for (text complexity) automatic assessment of longer texts from different genres. Completing this task can enable to increase the level of reading literacy among the Russian readers.

Corpus of Industrial Texts (CIT).zip

Corpus of Russian Academic Texts (CORAT).zip

Frequency Lists (FL).xlsx

Results of the "Concreteness-Abstractness" survey.zip