The article is devoted to the study of foreign and domestic experience in using augmented reality applications in classes in various disciplines, including tools that a teacher can use in everyday activities to increase the effectiveness of teaching school curriculum subjects. The review of modern mobile applications with augmented reality elements suitable for use in the educational process is presented. For example, the article describes the applications Quiver and Animal AR 3D Safari for kids; Surface math AR, Geometry — Augmented Reality, AR Geometry applications for studying mathematics; AR Human Atlas, Anatomy AR Book for studying medicine; Mondly AR for studying foreign languages. The new technology Merge Cube (a hologram in pupils' hands), which is used in applications Mr. Body and AR Medical to study anatomy, Galaxy Explorer to study the solar system, Museum Viewer to visit a virtual museum and study history is described in the article. The availability of augmented reality technology for use in the educational process is demonstrated on the basis of constructors such as HP Reveal, CoSpaces Edu and EV Toolbox. For example, HP Reveal and CoSpaces Edu were used to create interactive content such as video content and a dynamic animal gallery to explore the world around. CoSpaces Edu was used for creating interactive dialogs in English based on elements of block visual programming. EV Toolbox was used to create the simple application that was the project based on marker technology to study the history of the V. I. Vernadsky Crimean Federal University.

Дюличева Юлия Юрьевна — кандидат физико-математических наук, доцент ФГАОУ ВО «Крымский федеральный университет имени В. И. Вернадского». Адрес: 295007, Симферополь, просп. Академика Вернадского, 4. E-mail: dyulicheva_yu@mail.ru Исследование посвящено извлечению описаний математической тревожности из отзывов на массовые открытые онлайн-курсы по математике (MOOK) с помощью методов анализа текстовых данных. Эмоциональные состояния обучающихся, связанные с математической фобией, являются серьезным препятствием в изучении математики и получении базовых математических знаний, необходимых для будущей профессиональной деятельности. На платформах МООК накапливаются большие объемы данных, среди которых отзывы на онлайн-курсы представляют особый интерес. Эмпирическую основу исследования составили материалы 38 онлайн-курсов по математике на Udemy и 1898 отзывов обучающихся. Применение алгоритма анализа тональности VADER, кластерного анализа текстов отзывов с негативной тональностью на основе метода kMeans и векторного представления предложений с помощью модели представления языка BERT позволило выделить кластеры с описанием различных отрицательных эмоций, связанных с прошлым фрустрирующим опытом при изучении математики, кластер с описанием сожалений в связи с упущенными возможностями из-за негативного отношения к математике, а также кластер с описанием постепенного преодоления математической тревожности в процессе изучения онлайн-курсов по математике. Построенный граф знаний позволил визуализировать некоторые закономерности, связанные с различными отрицательными эмоциями, которые возникали у обучающихся при изучении математики.

The study is devoted to the development of a mobile application for the reconstruction in augmented reality of disappearing objects of cultural and historical heritage on the example of the Monzhene?s castle, also known as the Kessler?s estate. The importance of creating an archive of such digital twins - 3D-models for objects of cultural heritage that have been practically destroyed to the ground, the reconstruction of which is difficult, as well as for preserving the history and culture of ancestors, is noted. The effectiveness of using the developed application based on augmented reality technology in the educational process is confirmed by the results of a survey of 17 schoolchildren who used the application in the lessons of the history of their native land.

The article provides an overview of datasets and research areas in the field of educational data analysis based on natural language processing methods. The overview demonstrates the lack of datasets for the analysis of Russian-language reviews on MOOCs. Based on the scraping of reviews from the Stepik platform, a dataset of 5721 Russian-language reviews for MOOCs in mathematics, programming, biology, chemistry and physics was formed. A study of Russian-language reviews from the dataset was carried out based on descriptive statistics, frequency analysis of unigrams and bigrams, sentiment analysis using the dostoevsky python library with weighted F1-score for estimation accuracy of classification by sentiment as 74%. The descriptive characteristics of courses with respect to sentiments were detected based on unigrams analysis, the description of different aspects of learning content and difficulties encountered by students in learning MOOCs were detected based on bigrams analysis. The results of the sentiment analysis demonstrate the predominance of positive and neutral reviews of MOOCs in the studied dataset. The dataset is placed in the public domain Mendeley Data and will be useful to specialists in the field of text data analysis and the development of learning analytics tools.

The paper proposes the framework for auto-generation of the customer questions to help customers make choice of the best products based on their needs. The task of the optimal search organisation from millions of products is crucial for e-commerce systems. We propose the approach based on the following stages: the web-scraping stage of products reviews sites, pre-processing stage to detect key-phrases based on TextRank algorithm and POS-tagging, the subjective probabilities estimation stage to detect questions estimations and their ranking based on TextRank algorithm and Bayesian rule.