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

Deep Learning Methods in Sentiment Analysis

Student: Belova Anna

Supervisor: Oleg Durandin

Faculty: Faculty of Informatics, Mathematics, and Computer Science (HSE Nizhny Novgorod)

Educational Programme: Data Mining (Master)

Year of Graduation: 2017

This study has two major purposes: to apply deep learning to sentiment analysis task, and to try to understand neural network behavior in a way of finding important words. Classification of two corpora were done: English movie reviews and Russian restaurants reviews. To this data three recurrent neural networks were applied: Long Short Term Memory (LSTM), bidirectional LSTM (biLSTM) and Gated Recurrent Unit (GRU). Moreover, in the current research we developed and applied the methodology of finding important words that affect neural network’s decisions. This methodology allowed to detect two categories of important words for each of applied neural network. The first group is a list of words that improves accuracy of classificator. The second one negatively influence on the accuracy – deletion of these words increases classification quality.

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