Skip to main content Skip to main navigation menu Skip to site footer

Уважаемые пользователи! На нашем хостинге ведутся технические работы, на сайте могут быть ошибки. Приносим свои извинения за временные неудобства.

Bulletin of the Abai KazNPU, the series of "Physical and Mathematical Sciences"
Make a new submission
Vol. 69 No. 1 (2020)

USING OF LSTM NETWORKS IN SENTIMENT ANALYSIS OF DOCUMENTS IN KAZAKH LANGUAGE

Published June 2021
N.K. Kadyrbek+− М.Е. Mansurova+− М.Е Kyrgyzbayeva+−
Al-Farabi Kazakh National University, Almaty
Al-Farabi Kazakh National University, Almaty
Al-Farabi Kazakh National University, Almaty
Abstract

Due to the growing trust in information in social media resources, interest in the field of sentiment analysis is growing.
Because sentiment analysis is one of the main technologies for monitoring the opinions of millions of users of social
networks.
The article discusses the use of LSTM networks in the analysis of the tonality of texts in the Kazakh language. For
training the neural network, 1000 user reviews of mobile phones were used. The experiments were carried out in two
ways: in the first case, preprocessing of the analyzed reviews was carried out, in the second case, the preprocessing was
not carried out. The average value of the metric for assessing the quality of the pre-processed model reached 80%. This
indicator is 11% higher than for a model trained on data without preprocessing. The results of the study allowed us to
conclude that the preprocessing of the texts improves the quality of the model.

pdf (Рус)
Language

Қаз

Keywords
sentiment analysis natural language processing deep learning neural networks LSTM architecture
How to Cite

[1]
Кадырбек, Н., Мансурова, М. and Кыргызбаева, М. 2021. USING OF LSTM NETWORKS IN SENTIMENT ANALYSIS OF DOCUMENTS IN KAZAKH LANGUAGE. Bulletin of the Abai KazNPU, the series of "Physical and Mathematical Sciences". 69, 1 (Jun. 2021), 366–370.