Sentiment Analytics on Sarcasm Detection Using Bi-LSTM-1DCNN Model for Fake News Detection
Keywords:
Deep Learning, Sentiment Analytics, Fake News, Glove, Accuracy, Bi-LSTM-1DCNNAbstract
Finding expressive attitudes and states in text is the process of sentiment analysis, also referred to as opinion analysis. In this study, we offer a thorough investigation of sentiment analysis using the sophisticated fusion architecture of 1D convolutional neural networks (1DCNN) and Bidirectional Long Short-Term Memory (BI-LSTM). In order to understand the performance and ramifications of Glove and Word2Vec, two of the most notable word embeddings in the context of sentiment determination, they are compared in this investigation. The study encompasses a comprehensive assessment of critical performance indicators, mainly recall, accuracy, precision, and F1-score. Preliminary results conspicuously reveal a marked superiority of the BiLSTM+1DCNN model interfaced with Glove embeddings when juxtaposed against the Word2Vec variant. More specifically, the Glove-integrated model exhibited commendable precision values of 82% for positive sentiments and 78% for negative sentiments. Concurrently, recall metrics stood at 79% for positive and 80% for negative sentiments, leading to an impressive F1-score of 81% Positive sentiments and 82% for negative sentiment classes. This augmented performance is attributable to Glove's intricate semantic captures, owed to its training on extensive and diverse text corpora, thereby ensuring richer contextual information retrieval. In the quest to offer a visual and intuitive understanding, the research presents a suite of graphical representations: the accuracy graph elucidating model performance progression over epochs, the loss graph signifying the model's error rate, and the Receiver Operating Characteristic (ROC) graph portraying the model's capability in distinguishing sentiment polarities. A specialized comparison graph crystallizes the performance disparities between the two embeddings, fortifying the argument in favour of Glove's supremacy. Conclusively, the research underscores the paramountcy of selecting the apt embedding, with the Glove-based BiLSTM+1DCNN model emerging as the frontrunner for sentiment analytics tasks, owing to its impeccable balance between precision and recall, culminating in a laudable 83% accuracy.
Downloads
References
Ali, A.M. et al. (2022) ‘Deep Ensemble Fake News Detection Model Using Sequential Deep Learning Technique’, Sensors, 22(18), p. 6970. Available at: https://doi.org/10.3390/s22186970.
Alonso, M.A. et al. (2021) ‘Sentiment Analysis for Fake News Detection’, Electronics, 10(11), p. 1348. Available at: https://doi.org/10.3390/electronics10111348.
Bhutani, B. et al. (2019) ‘Fake News Detection Using Sentiment Analysis’, (August).
Chaubey, P.K. et al. (2022) ‘Sentiment Analysis of Image with Text Caption using Deep Learning Techniques’, Computational Intelligence and Neuroscience. Edited by V. Kumar, 2022, pp. 1–11. Available at: https://doi.org/10.1155/2022/3612433.
Chen, Q., Zhang, W. and Lou, Y. (2020) ‘Forecasting Stock Prices Using a Hybrid Deep Learning Model Integrating Attention Mechanism, Multi-Layer Perceptron, and Bidirectional Long-Short Term Memory Neural Network’, IEEE Access, 8, pp. 117365–117376. Available at: https://doi.org/10.1109/ACCESS.2020.3004284.
Dufraisse, E. et al. (2023) ‘MAD-TSC: A Multilingual Aligned News Dataset for Target-dependent Sentiment Classification’, in Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Stroudsburg, PA, USA: Association for Computational Linguistics, pp. 8286–8305. Available at: https://doi.org/10.18653/v1/2023.acl-long.461.
Galli, A. et al. (2022) ‘A comprehensive Benchmark for fake news detection’, Journal of Intelligent Information Systems, 59(1), pp. 237–261. Available at: https://doi.org/10.1007/s10844-021-00646-9.
Ju, X. et al. (2021) ‘Joint Multi-modal Aspect-Sentiment Analysis with Auxiliary Cross-modal Relation Detection’, in Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing. Stroudsburg, PA, USA: Association for Computational Linguistics, pp. 4395–4405. Available at: https://doi.org/10.18653/v1/2021.emnlp-main.360.
Kaur, G. and Sharma, A. (2023) ‘A deep learning-based model using hybrid feature extraction approach for consumer sentiment analysis’, Journal of Big Data, 10(1), p. 5. Available at: https://doi.org/10.1186/s40537-022-00680-6.
Khanam, Z. et al. (2021) ‘Fake News Detection Using Machine Learning Approaches’, IOP Conference Series: Materials Science and Engineering, 1099(1), p. 012040. Available at: https://doi.org/10.1088/1757-899X/1099/1/012040.
Song, G. and Huang, D. (2021) ‘A Sentiment-Aware Contextual Model for Real-Time Disaster Prediction Using Twitter Data’, Future Internet, 13(7), p. 163. Available at: https://doi.org/10.3390/fi13070163.
Anusha, M. and Leelavathi, R. (2023) ‘Sentiment Analytics on Sarcasm Detection Using Bi-LSTM-1DCNN Model for Fake News Detection’ Int. J. of Intelligent Engineering Informatics. Communicated.
Smith, J., Ivanov, G., Petrović, M., Silva, J., & García, A. Detecting Fake News: A Machine Learning Approach. Kuwait Journal of Machine Learning, 1(3). Retrieved from http://kuwaitjournals.com/index.php/kjml/article/view/142
Al-jammaz, R. A. ., Rawash, U. A. ., Kashef , N. M. ., & Ibrahim, E. M. . (2023). A Framework for Providing Augmented Reality as a Service Provided by Cloud Computing for E-Learning. International Journal on Recent and Innovation Trends in Computing and Communication, 11(2s), 20–31. https://doi.org/10.17762/ijritcc.v11i2s.6025
Aoudni, Y., Donald, C., Farouk, A., Sahay, K.B., Babu, D.V., Tripathi, V., Dhabliya, D. Cloud security based attack detection using transductive learning integrated with Hidden Markov Model (2022) Pattern Recognition Letters, 157, pp. 16-26.
García, A., Petrović, M., Ivanov, G., Smith, J., & Cohen, D. Enhancing Medical Diagnosis with Machine Learning and Image Processing. Kuwait Journal of Machine Learning, 1(4). Retrieved from http://kuwaitjournals.com/index.php/kjml/article/vi ew/143
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.
