Open AccessЗАСТОСУВАННЯ ПРОГРАМНОГО ПАКЕТУ R У НАУКОВИХ ДОСЛІДЖЕННЯХ МАЙБУТНІХ ФІЛОЛОГІВ
Author(s) -
Victoriia V. Zhukovska,
Oleksandr O. Mosiiuk,
Veronika V. Komarenko
Publication year - 2018
Publication title -
ìnformacìjnì tehnologìï ì zasobi navčannâ
Language(s) - English
Resource type - Journals
ISSN - 2076-8184
DOI - 10.33407/itlt.v66i4.2196
Subject(s) - philology , computer science , software , flexibility (engineering) , corpus linguistics , statistical analysis , field (mathematics) , computational linguistics , test (biology) , natural language processing , statistical hypothesis testing , artificial intelligence , mathematics , programming language , statistics , paleontology , feminism , political science , pure mathematics , law , biology
Corpus linguistics is a newly emerging field of study in applied linguistics that deals with construction, processing, and exploitation of text corpora. To date, a high-quality analysis of vast amounts of empirical language data provided by computerized corpora is impossible without computer technologies and relevant statistical methods. Therefore, teaching future philologists to effectively apply statistical computer programs is an important stage in their research training. The article discusses the possibilities of using one of the leading in Western linguistics, but not well-known in Ukraine, software packages for statistical data analysis – R statistical software environment – in the research by future philologists. The paper reveals the advantages and disadvantages of this program in comparison with other similar software packages (SPSS and Statistica) and provides Internet links to R self-learn tutorials. The flexibility and efficacy of R for linguistic research are demonstrated on the example of a statistical analysis of the use of hedges in the corpus of academic speech. For novice philologists to properly understand the peculiarities of conducting a statistical linguistic experiment with R, a detailed description of each stage of the study is provided. The statistical verification of hedges in the speech of students and lecturers was carried out using such statistical methods as the Kolmogorov–Smirnov test and the Mann-Whitney U Test. The article presents the developed algorithms to calculate the specified tests applying the built-in commands and various specialized library functions, created by R user community to enhance the functionality of this statistical software. Each script for statistical calculations in R is accompanied by a detailed description and interpretation of the results obtained. Further study of the issue will involve a number of activities aimed at raising awareness and improving skills of future philologists in using R statistical software, which is important for their professional development as researchers.