Sentiment Analysis of Electronic Social Media Based on Deep Learning

Vasily Derbentsev, Vitalii Bezkorovainyi, Andriy Matviychuk, Oksana Pomazun, Andrii Hrabariev, Alexey Hostryk

2022

Abstract

This paper describes Deep Learning approach of sentiment analyses which is an active research subject in the domain of Natural Language Processing. For this purpose we have developed three models based on Deep Neural Networks (DNNs): Convolutional Neural Network (CNN), and two models that combine convolutional and recurrent layers based on Long-Short-Term Memory (LSTM), such as CNN-LSTM and Bi-Directional LSTM-CNN (BiLSTM-CNN). As vector representations of words were used GloVe and Word2vec word embeddings. To evaluate the performance of the models, were used IMDb Movie Reviews and Twitter Sentiment 140 datasets, and as a baseline classifier was used Logistic Regression. The best result for IMDb dataset was obtained using CNN model (accuracy 90.1%), and for Sentiment 140 the model based on BiLSTM-CNN showed the highest accuracy (82.1%) correspondinly. The accuracy of the proposed models is a quite acceptable for practical use and comparable to state of the art models.

Paper Citation

in Harvard Style

Derbentsev V., Bezkorovainyi V., Matviychuk A., Pomazun O., Hrabariev A. and Hostryk A. (2022). Sentiment Analysis of Electronic Social Media Based on Deep Learning. In Proceedings of 10th International Conference on Monitoring, Modeling & Management of Emergent Economy - Volume 1: M3E2; ISBN 978-989-758-640-8, SciTePress, pages 163-175. DOI: 10.5220/0011932300003432

in Bibtex Style

@conference{m3e222,
author={Vasily Derbentsev and Vitalii Bezkorovainyi and Andriy Matviychuk and Oksana Pomazun and Andrii Hrabariev and Alexey Hostryk},
title={Sentiment Analysis of Electronic Social Media Based on Deep Learning},
booktitle={Proceedings of 10th International Conference on Monitoring, Modeling & Management of Emergent Economy - Volume 1: M3E2},
year={2022},
pages={163-175},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0011932300003432},
isbn={978-989-758-640-8},
}

in EndNote Style

TY - CONF

JO - Proceedings of 10th International Conference on Monitoring, Modeling & Management of Emergent Economy - Volume 1: M3E2
TI - Sentiment Analysis of Electronic Social Media Based on Deep Learning
SN - 978-989-758-640-8
AU - Derbentsev V.
AU - Bezkorovainyi V.
AU - Matviychuk A.
AU - Pomazun O.
AU - Hrabariev A.
AU - Hostryk A.
PY - 2022
SP - 163
EP - 175
DO - 10.5220/0011932300003432
PB - SciTePress