• A
  • A
  • A
  • ABC
  • ABC
  • ABC
  • А
  • А
  • А
  • А
  • А
Regular version of the site

Automatic Analysis of the Tonality of the Opinions about the Products of a Company

Student: Volkov Nikita

Supervisor: Vladimir Alexandrovich Fomichov

Faculty: Graduate School of Business

Educational Programme: Business Informatics (Bachelor)

Year of Graduation: 2018

Graduation qualification work on the topic: "Automatic Analysis of the Tonality of the Opinions about the Products of a Company" contains 46 pages of text, 10 figures, 7 tables, 6 formulas, 54 used sources, 1 appendix. Key words: text processing, sentiment analysis, tonality analysis, opinion mining, machine learning. The subject of the study is the methods of automatic opinion extraction from reviews of Internet users. The aim of the study is to create a scheme of a software that extracts users' opinions from reviews using the machine learning algorithm. In the paper algorithms of machine learning are analyzed, results of their testing and comparison are given. The subject area is electronic goods. The paper also describes the program for automatic processing of sites to extract users' opinions about a specific product in real time. Theoretical (analysis and comparison of text tonality extraction methods), empirical (collection of data resources that contain reviews) and mathematical methods (testing algorithms for the analysis of the tonality of the text) are used. The paper includes introduction, 3 chapters, proposed ways of further research and improvement, conclusion, list of literature, application. The introduction reveals the relevance of the research in the chosen area, the aim and objectives of the study are set, the subject of scientific research and methods of research are determined. In the first chapter, a literature review of this direction is made and their analysis is carried out. In the second chapter methods for analyzing the tonality of the text are selected and tested on the chosen subject area. The third chapter describes a software product for analyzing the tonality of text in real time. In conclusion the results of the research, the quality of the selected algorithms and the overall quality of the application are described.

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