Analysis and Filtration of User-generated Content in Web Development

Student: Smirnova Vladislava

Educational Programme: Computational Linguistics (Master)

Final Grade: 10

Year of Graduation: 2021

The aim of the study was solving three problems of analyzing and filtering user-generated text content. The list of the covered tasks consisted of obscene words detection, advertising detection and toxicity detection. As a part of the thesis modern approaches to these problems were analyzed. Experiments with implementation and evaluation of classical machine learning algorithms and neural networks were conducted. All the implemented neural models not only surpassed other machine learning algorithms, but also reached and in one case exceeded the state-of-the-art f-score and accuracy values for each task. The result of the work was realization of the open library for analyzing and filtering user-generated texts.

Full text (added May 31, 2021)

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