Quantitative and Semantic Analysis of Texts in Turkic Languages using Universal Declaration of Human Rights (UDHR) as a Corpus

Abstract

Thanks to Web, ubiquitous digital technologies and the increasing usage of digital environment by humans for work, entertainment, education and other activities, huge amounts of textual data is generated and available online. Text is the most informative and at the same time most sophisticated data type in terms of its comprehension by machines. The Text Analytics is a field that involves number of computer science disciplines to process textual data and transforms it into computer readable format suitable for another field of study Natural Language Processing to extract meaning.This research paper is an attempt to apply broad variety of statistical analysis methods to the corpora of several Turkic languages using Universal Declaration of Human Rights as a Corpus. Quantitative Text Analysis as a research area is focused on understanding the human language through statistics and numbers. As the language is the most effective tool to describe the social world, the Quantitative Text Analysis enables social exploration of the rial world at the scale.