Fake News Detection Using Long Short-Term Memory Networks and Natural Language Processing: A Deep Learning Approach with GloVe Word Embeddings
Article Sidebar
Main Article Content
Abstract
The exponential growth of fake news across digital media platforms poses a significant threat to public trust, democratic processes, and social stability. This paper presents the design, implementation, and experimental evaluation of an automated fake news detection system using Long Short-Term Memory (LSTM) networks combined with Natural Language Processing (NLP) pre-processing and GloVe pre-trained word embeddings. The proposed system is trained and evaluated on the Kaggle Fake News Dataset comprising 44,898 labeled English-language news articles. A comprehensive NLP pre-processing pipeline — including text cleaning, tokenization, stop-word removal, and lemmatization — transforms raw article text into structured input sequences. GloVe embeddings (100-dimensional) initialize the model's embedding layer, providing rich semantic representations with 86.4% vocabulary coverage. The LSTM-based architecture, incorporating spatial dropout and recurrent dropout regularization, achieves a test accuracy of 96.34% and a macro F1-score of 96.34%, significantly outperforming four traditional machine learning baselines: Naive Bayes (84.67%), Random Forest (89.76%), Logistic Regression (91.23%), and Support Vector Machine (93.48%). An ablation study quantifies the individual contribution of each system component. Error analysis identifies systematic misclassification patterns. The paper discusses ethical considerations, practical deployment implications, and directions for future research including transformer-based architectures, multilingual detection, and explainable AI integration.
Downloads
Article Details
Data Availability Statement
The dataset used in this study — the Kaggle Fake News Dataset — is publicly available at https://www.kaggle.com/c/fake-news/data. Pre-trained GloVe word embeddings (glove.6B.100d) are publicly available from the Stanford NLP Group at https://nlp.stanford.edu/projects/glove/. All implementation code, preprocessing scripts, and experimental results are available from the corresponding author upon reasonable request. All experiments were conducted with a fixed random seed (42) to ensure full reproducibility.
Section
This work is licensed under a Creative Commons Attribution 4.0 International License.
All articles published in Interdisciplinary Journal of AI, Machine Learning & Data Science (IJAIMLDS) are licensed under the terms of the Creative Commons Attribution 4.0 International License (CC BY 4.0).
This license allows others to share, copy, distribute, and adapt the work, provided that proper credit is given to the original author(s) and the source.
Authors retain copyright and grant Interdisciplinary Journal of AI, Machine Learning & Data Science (IJAIMLDS) the right of first publication.
How to Cite
References
[1] Shu, K., Sliva, A., Wang, S., Tang, J., & Liu, H. (2017). Fake news detection on social media: A data mining perspective. ACM SIGKDD Explorations Newsletter, 19(1), 22–36. https://doi.org/10.1145/3137597.3137600 DOI: https://doi.org/10.1145/3137597.3137600
[2] Zhou, X., & Zafarani, R. (2020). A survey of fake news: Fundamental theories, detection methods, and opportunities. ACM Computing Surveys, 53(5), 1–40. https://doi.org/10.1145/3395046 DOI: https://doi.org/10.1145/3395046
[3] Vosoughi, S., Roy, D., & Aral, S. (2018). The spread of true and false news online. Science, 359(6380), 1146–1151. https://doi.org/10.1126/science.aap9559 DOI: https://doi.org/10.1126/science.aap9559
[4] Lazer, D. M. J., et al. (2018). The science of fake news. Science, 359(6380), 1094–1096. https://doi.org/10.1126/science.aao2998 DOI: https://doi.org/10.1126/science.aao2998
[5] Allcott, H., & Gentzkow, M. (2017). Social media and fake news in the 2016 election. Journal of Economic Perspectives, 31(2), 211–236. https://doi.org/10.1257/jep.31.2.211 DOI: https://doi.org/10.1257/jep.31.2.211
[6] Wardle, C., & Derakhshan, H. (2017). Information Disorder: Toward an Interdisciplinary Framework for Research and Policy Making. Council of Europe Report DGI(2017)09.
[7] Ahmed, H., Traore, I., & Saad, S. (2018). Detecting opinion spams and fake news using text classification. Security and Privacy, 1(1), e9. https://doi.org/10.1002/spy2.9 DOI: https://doi.org/10.1002/spy2.9
[8] Pérez-Rosas, V., Kleinberg, B., Lefevre, A., & Mihalcea, R. (2018). Automatic detection of fake news. Proceedings of the 27th International Conference on Computational Linguistics (COLING 2018), 3391–3401.
[9] Castillo, C., Mendoza, M., & Poblete, B. (2011). Information credibility on Twitter. Proceedings of WWW 2011, 675–684. https://doi.org/10.1145/1963405.1963500 DOI: https://doi.org/10.1145/1963405.1963500
[10] Cortes, C., & Vapnik, V. (1995). Support-vector networks. Machine Learning, 20(3), 273–297. https://doi.org/10.1007/BF00994018 DOI: https://doi.org/10.1023/A:1022627411411
[11] Breiman, L. (2001). Random forests. Machine Learning, 45(1), 5–32. https://doi.org/10.1023/A:1010933404324 DOI: https://doi.org/10.1023/A:1010933404324
[12] Hochreiter, S., & Schmidhuber, J. (1997). Long short-term memory. Neural Computation, 9(8), 1735–1780. https://doi.org/10.1162/neco.1997.9.8.1735 DOI: https://doi.org/10.1162/neco.1997.9.8.1735
[13] Kim, Y. (2014). Convolutional neural networks for sentence classification. Proceedings of EMNLP 2014, 1746–1751. https://doi.org/10.3115/v1/D14-1181 DOI: https://doi.org/10.3115/v1/D14-1181
[14] Graves, A., & Schmidhuber, J. (2005). Framewise phoneme classification with bidirectional LSTM. Neural Networks, 18(5–6), 602–610. https://doi.org/10.1016/j.neunet.2005.06.042 DOI: https://doi.org/10.1016/j.neunet.2005.06.042
[15] Karimi, H., & Tang, J. (2019). Learning hierarchical discourse-level structure for fake news detection. Proceedings of NAACL 2019, 3432–3442. https://doi.org/10.18653/v1/N19-1347 DOI: https://doi.org/10.18653/v1/N19-1347
[16] Wang, W. Y. (2017). Liar, liar pants on fire: A new benchmark dataset for fake news detection. Proceedings of ACL 2017, 422–426. https://doi.org/10.18653/v1/P17-2067 DOI: https://doi.org/10.18653/v1/P17-2067
[17] Rashkin, H., Choi, E., Jang, J. Y., Volkova, S., & Choi, Y. (2017). Truth of varying shades: Analyzing language in fake news and political fact-checking. Proceedings of EMNLP 2017, 2931–2937. DOI: https://doi.org/10.18653/v1/D17-1317
[18] Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., & Salakhutdinov, R. (2014). Dropout: A simple way to prevent neural networks from overfitting. JMLR, 15(1), 1929–1958.
[19] Kingma, D. P., & Ba, J. (2015). Adam: A method for stochastic optimization. Proceedings of ICLR 2015. https://arxiv.org/abs/1412.6980
[20] Pennington, J., Socher, R., & Manning, C. D. (2014). GloVe: Global vectors for word representation. Proceedings of EMNLP 2014, 1532–1543. https://doi.org/10.3115/v1/D14-1162 DOI: https://doi.org/10.3115/v1/D14-1162
[21] Mikolov, T., Chen, K., Corrado, G., & Dean, J. (2013). Efficient estimation of word representations in vector space. Proceedings of ICLR 2013. https://arxiv.org/abs/1301.3781
[22] Devlin, J., Chang, M. W., Lee, K., & Toutanova, K. (2019). BERT: Pre-training of deep bidirectional transformers for language understanding. Proceedings of NAACL 2019, 4171–4186. DOI: https://doi.org/10.18653/v1/N19-1423
[23] Kula, S., Choraś, M., Kozik, R., Ksieniewicz, P., & Woźniak, M. (2021). Sentiment analysis for fake news detection by means of neural networks. Computational Science — ICCS 2021, 152–163.
[24] Manning, C. D., Raghavan, P., & Schütze, H. (2008). Introduction to Information Retrieval. Cambridge University Press. DOI: https://doi.org/10.1017/CBO9780511809071
[25] Bird, S., Loper, E., & Klein, E. (2009). Natural Language Toolkit (NLTK) [Software]. Retrieved from https://www.nltk.org
[26] Abadi, M., et al. (2016). TensorFlow: Large-scale machine learning on heterogeneous systems. arXiv:1603.04467.
[27] Chollet, F. (2015). Keras [Software]. GitHub. Retrieved from https://github.com/keras-team/keras
[28] Pedregosa, F., et al. (2011). Scikit-learn: Machine learning in Python. JMLR, 12, 2825–2830.
[29] Powers, D. M. W. (2011). Evaluation: From precision, recall and F-measure to ROC, informedness, markedness and correlation. JMLT, 2(1), 37–63.
[30] Kaggle. (2018). Fake News Dataset [Data set]. Retrieved from https://www.kaggle.com/c/fake-news/data
[31] Ribeiro, M. T., Singh, S., & Guestrin, C. (2016). Why should I trust you?: Explaining the predictions of any classifier. Proceedings of ACM SIGKDD 2016, 1135–1144. DOI: https://doi.org/10.1145/2939672.2939778
[32] Lundberg, S. M., & Lee, S. I. (2017). A unified approach to interpreting model predictions. Advances in NeurIPS 2017, 30.
[33] LeCun, Y., Bengio, Y., & Hinton, G. (2015). Deep learning. Nature, 521(7553), 436–444. DOI: https://doi.org/10.1038/nature14539
[34] Yang, Z., Yang, D., Dyer, C., He, X., Smola, A., & Hovy, E. (2016). Hierarchical attention networks for document classification. Proceedings of NAACL 2016, 1480–1489. DOI: https://doi.org/10.18653/v1/N16-1174
[35] Honnibal, M., Montani, I., Van Landeghem, S., & Boyd, A. (2020). spaCy: Industrial-strength NLP [Software]. https://doi.org/10.5281/zenodo.1212303