Application of Machine Learning Techniques to Undesirable Comments Detection on the Internet

Student: Gorodetsky Yaroslav

Supervisor: Michael Levashov

Educational Programme: Information Security Management (Master)

Year of Graduation: 2018

With constant development of information technologies and the Internet, it becomes necessary to use and integrate automated content filtering systems. Without the use of such systems, content moderation requires human resources. Hence, automation problem of this process is topical. The paper offers a possible solution to this problem by an example of performing identification of undesirable comments on the Internet. It describes theoretical approaches and their application to solving the task using machine learning techniques. The result of the work is a prototype of the classifier for identification of undesirable comments. Such classifier can be applied in the field of information security, e.g. content filtration and moderation of web pages.

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