The article presents the results of an original study aimed at finding (1) frequency fluctuations of the term ‘readability’ in American discourse and its Russian equivalent ‘chitabelnost’ in Russian discourse over the period from 1920s to the present; and (2) semantic similarities and differences between the English term ‘readability’ and its Russian equivalent ‘chitabelnost’ over the same period of time. A contrastive analysis of the words testified to inconsiderable differences in the semantic structures of the terms in the period under study: the term ‘readability’ has been used with the following meanings: (1) ‘the quality of being legible or decipherable’ and (2) ‘the quality of being easy or enjoyable to read’. The Russian equivalent ‘chitabelnost’ has two contemporary meanings similar to the aforementioned English meanings as well as the obsolete ‘library book checkouts’. With the help of the Google NgramViewer, we identified the 1980s frequency peak of both terms when the modern notion of the concepts was formed. The research into the topical context of readability as ‘the quality of being easy or enjoyable to read’ demonstrated empiricist tendencies in American studies focused on two types of parameters, i.e. the ‘objective’ parameters of texts, i.e. sentence length, word counts, number of high/low frequency words, ratio of high/low frequency words to total words, sentence complexity, etc. and ‘individual’ variables affecting a potential reader, such as ‘word familiarity’, cognitive and linguistic abilities, cultural and topic knowledge, etc. The Russian school’s view, until the 1970s, had traditionally been more holistic and ‘biased’ towards an individuals’ factors. The results of the study have the potential to contribute to cross-linguistic research in the area of text readability assessment, semantics, and scientific literature searches.
A Machine Learning Approach to Persian Text Readability Assessment Using a Crowdsourced Dataset
