TY - GEN

T1 - Sentiment Analysis in Uzbek Language Texts: a Study Using Neural Networks and Algorithms

AU - Akhmedov, Ergash Yu

AU - Palchunov, Dmitriy E.

AU - Khaitboeva, Durdona Z.

AU - Ibragimov, Mukhiddin F.

AU - Sultanov, Otojon R.

AU - Rakhimova, Laylo S.

N1 - Conference code: 25

PY - 2024

Y1 - 2024

N2 - 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.

AB - 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.

KW - activation function

KW - deep learning

KW - lemma

KW - neuron weight

KW - recurrent neural network

KW - synapses

KW - token

UR - https://www.scopus.com/record/display.uri?eid=2-s2.0-85201931319&origin=inward&txGid=1a61446520dd393e497dda1a197a8c8c

UR - https://www.mendeley.com/catalogue/48318571-8498-357c-81d2-15d6d2c5ee4c/

U2 - 10.1109/EDM61683.2024.10615017

DO - 10.1109/EDM61683.2024.10615017

M3 - Conference contribution

SN - 9798350389234

T3 - International Conference of Young Specialists on Micro/Nanotechnologies and Electron Devices, EDM

SP - 2460

EP - 2464

BT - International Conference of Young Specialists on Micro/Nanotechnologies and Electron Devices, EDM

PB - IEEE Computer Society

T2 - 25th IEEE International Conference of Young Professionals in Electron Devices and Materials

Y2 - 28 June 2024 through 2 July 2024

ER -