Self-Attentive CNN+BERT: An Approach for Analysis of Sentiment on Movie Reviews Using Word Embedding
Keywords:
Sentiment Analysis, Text Classfication, LSTM, Deep LearningAbstract
Social media has developed into a vast user opinion repository in the modern day. Due to the sophistication of the internet and technological developments, a great amount of data is being generated from a variety of sources, including websites and social blogging. Websites and blogs are being used as means for gathering product reviews in real time. On the other hand, the proliferation of blogs hosted on cloud servers has led to a significant amount of data, including thoughts, opinions, and evaluations. As such, techniques for deriving actionable insights from massive amounts of data, classifying it, and forecasting end-user actions or emotions are desperately needed. People use social media platforms to instantly share their ideas in the present day. It is difficult to analyze and draw conclusions from this data for sentiment analysis. Even with automated machine learning methods, it is still difficult to extract meaningful semantic concepts from a sparse review representation. Word embedding improves text categorization by resolving word semantics and sparse matrix problems. This paper presents a novel framework to capture semantic links between neighboring words by fusing word embedding with BERT. A weighted self-attention method is also used to find important phrases in the reviews. by means of an empirical investigation utilizing the IMDB data-set. In order to address sentiment analysis, this work presents a Hybrid CNN-BERT Model that combines BERT with an extremely sophisticated CNN model. First, initial word embedding are trained using the Word to Vector (Word2Vec) technique, which converts text strings into numerical vectors, calculates word distances, and groups related words according to their meaning. The suggested model then integrates long-term dependencies with characteristics gleaned from convolution and global max-pooling layers during word embedding. For improved accuracy, the model uses rectified linear units, normalizing, and dropout technologies. The performance of proposed model in terms of accuracy is 95.91%, pression is 96..80%, recall is 95.07%, f1 score is 95.93%.
Downloads
References
Iftikhar, S., Alluhaybi, B., Suliman, M., Saeed, A., & Fatima, K. (2023). Amazon products reviews classification based on machine learning, deep learning methods and BERT. TELKOMNIKA (Telecommunication Computing Electronics and Control), 21(5), 1084-1101.
Yenkikar, A., & Babu, C. N. (2023). AirBERT: A fine-tuned language representation model for airlines tweet sentiment analysis. Intelligent Decision Technologies, 17(2), 435-455.
Muftie, F., & Haris, M. (2023, August). IndoBERT Based Data Augmentation for Indonesian Text Classification. In 2023 International Conference on Information Technology Research and Innovation (ICITRI) (pp. 128-132). IEEE.
Muftie, F., & Haris, M. (2023, August). IndoBERT Based Data Augmentation for Indonesian Text Classification. In 2023 International Conference on Information Technology Research and Innovation (ICITRI) (pp. 128-132). IEEE.
Motitswane, O. G. (2023). Machine learning and deep learning techniques for natural language processing with application to audio recordings (Doctoral dissertation, North-West University (South Africa)).
Sultana, M. (2023). An Exploration of Dialog Act Classification in Open-domain Conversational Agents and the Applicability of Text Data Augmentation.
S. Nayak, Sonia and Y. K. Sharma, "Efficient Machine Leaning Algorithms for Sentiment Analysis In Car Rental Service," 2023 International Conference on Computational Intelligence and Sustainable Engineering Solutions (CISES), Greater Noida, India, 2023, pp. 452-463, doi: 10.1109/CISES58720.2023.10183435.
Khan, A., Hopkins, J., & Gunes, H. (2021, September). Multi-dimensional Affect in Poetry (POCA) Dataset: Acquisition, Annotation and Baseline Results. In 2021 9th International Conference on Affective Computing and Intelligent Interaction (ACII) (pp. 1-8). IEEE.
Thapa, A. (2023). Sentiment Analysis On Juvenile Delinquency Using BERT Embeddings (Doctoral dissertation, Dublin, National College of Ireland).
Chinnalagu, A., & Durairaj, A. K. (2021). Context-based sentiment analysis on customer reviews using machine learning linear models. PeerJ Computer Science, 7, e813.
Narayan, Vipul, et al. "7 Extracting business methodology: using artificial intelligence-based method." Semantic Intelligent Computing and Applications 16 (2023): 123
Narayan, Vipul, et al. "A Comprehensive Review of Various Approach for Medical Image Segmentation and Disease Prediction." Wireless Personal Communications 132.3 (2023): 1819-1848.
Mall, Pawan Kumar, et al. "Rank Based Two Stage Semi-Supervised Deep Learning Model for X-Ray Images Classification: AN APPROACH TOWARD TAGGING UNLABELED MEDICAL DATASET." Journal of Scientific & Industrial Research (JSIR) 82.08 (2023): 818-830.
Narayan, Vipul, et al. "Severity of Lumpy Disease detection based on Deep Learning Technique." 2023 International Conference on Disruptive Technologies (ICDT). IEEE, 2023.
Saxena, Aditya, et al. "Comparative Analysis Of AI Regression And Classification Models For Predicting House Damages İn Nepal: Proposed Architectures And Techniques." Journal of Pharmaceutical Negative Results (2022): 6203-6215.
Kumar, Vaibhav, et al. "A Machine Learning Approach For Predicting Onset And Progression"“Towards Early Detection Of Chronic Diseases “." Journal of Pharmaceutical Negative Results (2022): 6195-6202.
Chaturvedi, Pooja, Ajai Kumar Daniel, and Vipul Narayan. "Coverage Prediction for Target Coverage in WSN Using Machine Learning Approaches." (2021).
Chaturvedi, Pooja, A. K. Daniel, and Vipul Narayan. "A Novel Heuristic for Maximizing Lifetime of Target Coverage in Wireless Sensor Networks." Advanced Wireless Communication and Sensor Networks. Chapman and Hall/CRC 227-242.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.
IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.
