Computer Methods for Thematic Modeling of Textbooks Collection in Natural Language
УДК 519.67+004.942
Abstract
The paper presents the development results of computer methods for analyzing text data and assessing classification inaccuracies at the stages of thematic modeling. This study uses as an example the task to process textual data of a collection of graduate qualification works prepared and defended by students of Altai State University, Faculty of Mathematics and IT in recent years.
The main results obtained in the paper are listed as follows. Relevant application areas and directions for computer methods and thematic modeling in the educational process are identified. Justification of the general algorithm for solving the problem of the thematic analysis of collections of educational materials is carried out. Information technologies for thematic modeling are developed, and estimation of analysis errors on a set of test documents is obtained. It is shown that computer-based methods of thematic modeling and information technology to support them can be used both in the educational process and in the development of educational and methodological documents.
Downloads
Metrics
References
Ерланова Р.Е. и др. Тематическое моделирование текстовых учебных материалов по информатике средствами языка R // Известия АлтГУ. 2018. № 4(102). DOI: 10.14258/izvasu(2018)4-12.
Махина Е. Д., Пальчунов Д. Е. Программная система для определения речевых действий в текстах естественного языка // Вестник НГУ. Серия : Информационные технологии. 2018. Т. 16. № 4. DOI: 10.25205/1818-7900-2018-16-4-95-106.
Коляда А.С. и др. Применение латентного размещения Дирихле для анализа публикаций из наукометрических баз данных // Pratsi. 2014. № 1 (43).
Леонова Ю. В., Федотов А.М. Извлечение знаний и фактов из текстов диссертаций и авторефератов // Системный анализ и информационные технологии : Тр. V Меж. конф. Красноярск, 2013. Т. 1.
Dezhao S., Schilder F., Smiley C., Brew C., Zielund T., Bretz H., Martin R., Dale C., Pomerville S., Duprey J., Miller T., and Harrison J. TR Discover: a natural language interface for querying and analyzing interlinked datasets. Proc. 14th Intern. conf. on the Semantic Web: ISWC 2015. Springer Intern. Publ., 2015.
Chen F. Topic Modeling of Document Metadata for Visualizing Collaborations over Time / P. Chiu, S. Lim // Proc. of the Int. Conf. on Intelligent User Interfaces (IUI), 2016. DOI: 10.1145/2856767.2856787.
Бабкина Н.С., Смолякова Л.Л. Проблемы реализации тематического моделирования в учебном процессе : сб. научн. ст. Межд. конф «Ломоносовские чтения на Алтае: фундаментальные проблемы науки и техники». 2018. URL: https://sites.google.com/site/lomchten/ .
Федотов А.М., Прозоров О.В., Федотова О.А., Бапанов А.А. О подходе к тематической классификации документов // Вестник НГУ. Серия : Информационные технологии. 2017. Т. 15. № 1.
Половикова О.Н., Бабкина Н.С., Смолякова Л.Л. Анализ проблематики тематического моделирования // МАК : «Математики — Алтайскому краю» : сб. трудов Всерос. конф. по математике с междунар. участием. Барнаул, 2018.
Леонова Ю.В., Федотов А.М., Федотова О.А. О подходе к классификации авторефератов диссертаций по темам // Вестник НГУ Серия : Информационные технологии. 2017. Т. 15. № 1. DOI: 10.25205/1818-7900-2017-15-1-47-58.
Izvestiya of Altai State University is a golden publisher, as we allow self-archiving, but most importantly we are fully transparent about your rights.
Authors may present and discuss their findings ahead of publication: at biological or scientific conferences, on preprint servers, in public databases, and in blogs, wikis, tweets, and other informal communication channels.
Izvestiya of Altai State University allows authors to deposit manuscripts (currently under review or those for intended submission to Izvestiya of Altai State University) in non-commercial, pre-print servers such as ArXiv.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License (CC BY 4.0) that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
