A comparative study of deep learning models for sentiment analysis of social media texts
No Thumbnail Available
Date
2022-11
Journal Title
Journal ISSN
Volume Title
Publisher
CEUR Workshop Proceedings
Abstract
Sentiment analysis is a challenging task in natural language processing, especially for social media texts, which are often informal, short, and noisy. In this paper, we present a comparative study of deep learning models for sentiment analysis of social media texts. We develop three models based on deep neural networks (DNNs): a convolutional neural network (CNN), a CNN with long short-term memory (LSTM) layers (CNN-LSTM), and a bidirectional LSTM with CNN layers (BiLSTM-CNN). We use GloVe and Word2vec word embeddings as vector representations of words. We evaluate the performance of the models on two datasets: IMDb Movie Reviews and Twitter Sentiment 140. We also compare the results with a logistic regression classifier as a baseline. The experimental results show that the CNN model achieves the best accuracy of 90.1% on the IMDb dataset, while the BiLSTM-CNN model achieves the best accuracy of 82.1% on the Sentiment 140 dataset. The proposed models are comparable to state-of-the-art models and suitable for practical use in sentiment analysis of social media texts.
Description
Keywords
sentiment analysis, social media, deep learning, convolutional neural networks, long short-term memory, word embeddings
Citation
A comparative study of deep learning models for sentiment analysis of social media texts [Electronic resource] / Vasily D. Derbentsev, Vitalii S. Bezkorovainyi, Andriy V. Matviychuk [et al.] // Monitoring, Modeling & Management of Emergent Economy (M3E2–MLPEED 2022) : proceedings of the selected and revised papers of 10th international conference, November 17–18, 2022, Virtual, Online (postponed due to Russian invasion of Ukraine) / [ed.: H. B. Danylchuk, S. O. Semerikov]. – Electronic text data. – Kryvyi Rih, 2022. – Vol. 3465 : Machine Learning for Prediction of Emergent Economy Dynamics. – P. 168–188. – Title from screen.