Python Language In The Development Of Computational Competencies In Humanities Education
Anatoly B. Mantusov, Zamira Badmaevna Dorzhinova · The European Proceedings of Social & Behavioural Sciences · 2021
This article examines the development of computational competencies in undergraduate and graduate students of humanities, studying philology through the use of free and open-source software such as the Python programming language on the example of quantitative text analysis using Python programming language libraries such as NumPy and SciPy, as well as Pandas. The leading platform for building Python programs to handle natural language data is NaturalLanguageToolkit, which is free and open-source software. For morphological analysis: obtaining the lemma or base of a given token and, if necessary, morphological parameters, we used the freeware program MyStem. Pandas is a package, an add-on to the NumPy library, that provides an efficient implementation of the DataFrame class. In Pandas we used structures like Series and Dataframe, and used the library matplotlib to visualize the result of cluster analysis as a dendrogram. The choice of training content concerning the application of these methods to arrays of textual data depends on the principles of professional orientation of training and ethno-cultural connotation of education, so the example of cluster analysis uses the Kalmykian folk epic "Dzhangar" and the sample questions to be proposed during the analysis of the example, choosing the object of subsequent application of the proposed method in the context of forming a professional picture of the world. In addition, a specific issue is the critical analysis of the processing of text analysis results obtained by applying the studied methods to further develop the teaching of computer science.