Sentiment Analysis in Uzbek Language Texts: a Study Using Neural Networks and Algorithms | Sciact - Система учета научной деятельности ИМ СО РАН

Sentiment Analysis in Uzbek Language Texts: a Study Using Neural Networks and Algorithms Научная публикация

Конференция

IEEE 25th International Conference of Young Professionals in Electron Devices and Materials
28 июн. - 2 июл. 2024 , Республика Алтай

Сборник

2024 IEEE 25th International Conference of Young Professionals in Electron Devices and Materials (EDM)
Сборник, 2024. 2673 c. ISBN 979-8-3503-8923-4.

Вых. Данные

Год: 2024, Страницы: 2460-2464 Страниц : 5 DOI: 10.1109/edm61683.2024.10615017

Ключевые слова

activation function, deep learning, lemma, neuron weight, recurrent neural network, synapses, token

Авторы

Akhmedov Ergash Yu. ¹ , Palchunov Dmitriy E. ² , Khaitboeva Durdona Z. ³ , Ibragimov Mukhiddin F. ³ , Sultanov Otojon R. ³ , Rakhimova Laylo S. ³

Организации

1	Novosibirsk State University,IT Department,Novosibirsk,Russia
2	Sobolev Institute of Mathematics,DSc., Academian of REA Leading researcher,Novosibirsk,Russia
3	Urgench branch of the Tashkent University of Information Technologies named after Muhammad al-Khwarizmi,Software engineering Department,Urgench,Uzbekistan

Информация о финансировании (1)

Институт математики им. С.Л. Соболева СО РАН

FWNF-2022-0011

The study of user opinions about products and services expressed in the form of unstructured texts in the Uzbek language and accessible through social networks is an important area of research. User opinion surveys measure user satisfaction and feedback about products and services. Analysis of unstructured texts in Uzbek written by users on social networks can help in identifying the positive and negative aspects of products and services, as well as understanding the needs and preferences of users. To conduct research, it is necessary to use natural language processing and text analysis methods. This may include the use of machine learning algorithms, sentiment analysis, topic modeling and other techniques to extract information from unstructured text data. An important aspect of such research is taking into account the features of the Uzbek language, its vocabulary and grammar. It is necessary to take into account context, semantics and cultural characteristics when analyzing user opinions in the Uzbek language. To achieve this goal, it is necessary to conduct deep learning experiments on Uzbek language text classes using long short - term memory models, convolutional neural networks and transformer-based deep learning models such as the multilingual Bidirectional Encoder Representations from Transformers model

Akhmedov E.Y. , Palchunov D.E. , Khaitboeva D.Z. , Ibragimov M.F. , Sultanov O.R. , Rakhimova L.S.
Sentiment Analysis in Uzbek Language Texts: a Study Using Neural Networks and Algorithms
В сборнике 2024 IEEE 25th International Conference of Young Professionals in Electron Devices and Materials (EDM). 2024. – C.2460-2464. – ISBN 979-8-3503-8923-4. DOI: 10.1109/edm61683.2024.10615017 Scopus OpenAlex

Опубликована в печати:	5 авг. 2024 г.
Опубликована online:	5 авг. 2024 г.

Scopus:	2-s2.0-85201931319
OpenAlex:	W4401329501

БД	Цитирований
Scopus	1