Enhancing Sentiment Analysis with a CNN-Stacked LSTM Hybrid Model
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 mention...
Saved in:
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
EDP Sciences
2025-01-01
|
| Series: | ITM Web of Conferences |
| Online Access: | https://www.itm-conferences.org/articles/itmconf/pdf/2025/01/itmconf_dai2024_02002.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1825206541464109056 |
|---|---|
| author | Shao Shuaijie |
| author_facet | Shao Shuaijie |
| author_sort | Shao Shuaijie |
| collection | DOAJ |
| description | 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. |
| format | Article |
| id | doaj-art-0d008652581845019d70817b565bd696 |
| institution | Kabale University |
| issn | 2271-2097 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | EDP Sciences |
| record_format | Article |
| series | ITM Web of Conferences |
| spelling | doaj-art-0d008652581845019d70817b565bd6962025-02-07T08:21:10ZengEDP SciencesITM Web of Conferences2271-20972025-01-01700200210.1051/itmconf/20257002002itmconf_dai2024_02002Enhancing Sentiment Analysis with a CNN-Stacked LSTM Hybrid ModelShao Shuaijie0Shijiazhuang No.2 High SchoolThis 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.https://www.itm-conferences.org/articles/itmconf/pdf/2025/01/itmconf_dai2024_02002.pdf |
| spellingShingle | Shao Shuaijie Enhancing Sentiment Analysis with a CNN-Stacked LSTM Hybrid Model ITM Web of Conferences |
| title | Enhancing Sentiment Analysis with a CNN-Stacked LSTM Hybrid Model |
| title_full | Enhancing Sentiment Analysis with a CNN-Stacked LSTM Hybrid Model |
| title_fullStr | Enhancing Sentiment Analysis with a CNN-Stacked LSTM Hybrid Model |
| title_full_unstemmed | Enhancing Sentiment Analysis with a CNN-Stacked LSTM Hybrid Model |
| title_short | Enhancing Sentiment Analysis with a CNN-Stacked LSTM Hybrid Model |
| title_sort | enhancing sentiment analysis with a cnn stacked lstm hybrid model |
| url | https://www.itm-conferences.org/articles/itmconf/pdf/2025/01/itmconf_dai2024_02002.pdf |
| work_keys_str_mv | AT shaoshuaijie enhancingsentimentanalysiswithacnnstackedlstmhybridmodel |