Service for Propaganda Detection in News Articles

Student: Chernov Sergei

Educational Programme: System and Software Engineering (Master)

Year of Graduation: 2020

Nowadays reading news is an essential part of daily life. However, information we get from various resources is not always objective. One of the challenges for attentive newspaper readers is detecting information affected by propaganda. This paper is dedicated to propaganda detection problem. In this work, the definition of propaganda and its types are presented with examples. Propaganda detection as language modeling task is analyzed and one of its subtasks – fragment-level classification – is investigated. BERT model with fine-tuning is used as neural network architecture for implementation. Model is implemented using Python and its frameworks. For propaganda detection tool usage service with REST API has been designed and developed on Java programming language. This paper contains 55 pages, 5 chapters, 13 illustrations, 43 bibliography items, 6 appendices. Keywords: language modeling, propaganda detection, fragment level classification (FLC), BERT, REST API.

Student Theses at HSE must be completed in accordance with the University Rules and regulations specified by each educational programme.

Summaries of all theses must be published and made freely available on the HSE website.

The full text of a thesis can be published in open access on the HSE website only if the authoring student (copyright holder) agrees, or, if the thesis was written by a team of students, if all the co-authors (copyright holders) agree. After a thesis is published on the HSE website, it obtains the status of an online publication.

Student theses are objects of copyright and their use is subject to limitations in accordance with the Russian Federation’s law on intellectual property.

In the event that a thesis is quoted or otherwise used, reference to the author’s name and the source of quotation is required.

Search all student theses