Issue |
ITM Web Conf.
Volume 70, 2025
2024 2nd International Conference on Data Science, Advanced Algorithm and Intelligent Computing (DAI 2024)
|
|
---|---|---|
Article Number | 02002 | |
Number of page(s) | 7 | |
Section | Machine Learning in Healthcare and Finance | |
DOI | https://doi.org/10.1051/itmconf/20257002002 | |
Published online | 23 January 2025 |
Enhancing Sentiment Analysis with a CNN-Stacked LSTM Hybrid Model
Shijiazhuang No.2 High School, 050000, Shijiazhuang, China
Corresponding author: shawn@shawnshao.org
This paper focuses on developing a new hybrid model to solve sentiment analysis problems in Natural language processing. Sentiment analysis is a key branch of Natural language processing (NLP) and new models with better performance can boost the development of machine learning. The new model mentioned in this research is a hybrid model containing convolutional neural network (CNN), stacked multi-layer long short-term memory (LSTM) and max pooling layers. This model uses CNN for its advantage of capturing local features in the sequence after the embedding process, and LSTM for its advantage of capturing long-term dependencies in such sequential data after CNN layer. The global max pooling layer can better organize the entire sequence. This model has been tested to show that it has a better performance than previously mentioned models when solving the sentiment analysis task based on IMDB dataset provided by TensorFlow. Introducing this new model in sentiment analysis may open new avenues for research. The performance of the model can be further improved, offering valuable insights for future hybrid model development in machine learning tasks.
© The Authors, published by EDP Sciences, 2025
This is an Open Access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.