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

Comparison of Approaches to Building Ensemble Models in the Problem of Analysis of User Reviews

Student: Khomyuk Grigoriy

Supervisor: Liudmila Zhukova

Faculty: HSE Tikhonov Moscow Institute of Electronics and Mathematics (MIEM HSE)

Educational Programme: Applied Mathematics (Bachelor)

Year of Graduation: 2021

Analyzing generally accessible information provided by users in social media might improve customer service in various manufacturing companies and companies that provide services to individuals. Such information might be presented by customers’ reviews about the product or service on different websites. Basic machine learning algorithms often assist heavily in solving the problem of identifying the negativity of the feedback. The purpose of the work is to compare the approaches to constructing ensemble models and to study the effectiveness of such models in the problems of classifying customer reviews. The object of this research is ensemble methods for constructing models that can outperform single basic algorithms in forecasting quality. During the research, methods of preprocessing text data, methods of ensemble classifiers were studied and described, and a comparative analysis of the models was carried out according to various metrics of forecasting quality. The result of this study is the classification model with high predictive power, the approach to the construction of which can be used in various tasks of unstructured data classification.

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