An Ensemble Deep Learning Model Based on Ideal Weighting Method for Fake News Detection on Social Media
Article Sidebar
Main Article Content
Abstract
Fake news is an important problem of great impact in society and business. Accurate automated fake news detection can help reduce the spread of fake news, social turmoil and business damage in a timely manner. This research presents an ensemble deep learning based on ideal weighting method for detecting fake news from ISOT fake news dataset which were collected from 44,898 of the English news websites. It is divided into two types, including the 21,417 of real news and 23,481 of fake news. Firstly, text pre-processing was used to transform unstructured data into structured data. Secondly, three deep learning models (including CNN-SGD, CNN-RMSProp and CNN-Adam) were tested. Next, the values of accuracy for models were used to calculate the ideal weighting factors of each model. After that, these weights were utilized to combine the prediction models using Weight Sum Method (WSM). Finally, the proposed ensemble deep learning model was tested. The results shown that the proposed model is effective to tackle the ISOT fake news dataset, which are significantly better than other traditional approaches. The accuracy values of the proposed ensemble deep learning model, CNN-SGD, CNN-RMSProp and CNN-Adam were 98.32%, 75.36%, 98.20% and 98.04% respectively. For future work, the proposed method should be tested with more cases to enhance the reliability.
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
Articles published in Journal of Industrial Technology Ubon Ratchathani Rajabhat University both hard copy and electronically are belonged to the Journal.
References
Umer M, Imtiaz Z, Ullah S, Mehmood A, Choi GS, On B-W. Fake news stance detection using deep learning architecture (CNN-LSTM). IEEE Access. 2020; 8: 156695–706.
Ajao O, Bhowmik D, Zargari S. Fake News Identification on Twitter with Hybrid CNN and RNN Models. 9th International Conference on Social Media and Society. 2018. Copenhagen.
ANTI-FAKE NEWS CENTER THAILAND. ANTI-FAKE NEWS CENTER THAILAND [Internet]. 2020 [cited 2021 Jul 15]. Available from: https://www.antifakenewscenter.com.
Nasir JA, Khan OS, Varlamis I. Fake news detection: A hybrid CNN-RNN based deep learning approach. International Journal of Information Management Data Insights. 2021; 1(1): 100007.
Awan MJ. Fake News Classification Bimodal using Convolutional Neural Network and Long Short-Term Memory. Artic Int J Emerg Technol Learn [Internet]. 2020 [cited 2021 July 21] Available from: https://www.researchgate.net/publication/347886404.
Dos Santos C, Zadrozny B. Learning character-level representations for part-of-speech tagging. International Conference on Machine Learning. 2014. p. 1818–26. PMLR.
Abdi A, Shamsuddin SM, Hasan S, Piran J. Deep learning-based sentiment classification of evaluative text based on Multi-feature fusion. Information Processing Management. 2019; 56(4): 1245–59.
Kumar A, Jaiswal A. Deep learning based sentiment classification on user-generated big data. Recent Advances in Computer Science and Communications (Formerly: Recent Patents Computer Science). 2020; 13(5): 1047–56.
Onan A. Deep learning based sentiment analysis on product reviews on Twitter. International Conference on Big Data Innovations and Applications. 2019. p. 80–91. Springer.
Kumar S, Asthana R, Upadhyay S, Upreti N, Akbar M. Fake news detection using deep learning models: A novel approach. Trans Emerg Telecommun Technol. 2020; 31(2): e3767.
Ge L, Hang R, Liu Y, Liu Q. Comparing the performance of neural network and deep convolutional neural network in estimating soil moisture from satellite observations. Remote Sensing. 2018; 10(9): 1327.
Ruder S. An overview of gradient descent optimization algorithms. arXiv Preprint arXiv:1609.
2016.
Kingma DP, Ba J. Adam: A method for stochastic optimization. arXiv Preprint arXiv:1412.6980. 2014.
Sarawoot Boonkidram NS. Physical Quality Investigation of Germinated Brown Rice by using Image Processing. Journal of Information Science and Technology. 2020; 10(2): 101–9.
Cai J, Li J, Li W, Wang J. Deeplearning model used in text classification. 15th International Computer Conference on Wavelet Active Media Technology and Information Processing (ICCWAMTIP). 2018 p. 123-6. IEEE.
Ahmed H, Traore I, Saad S. Detecting opinion spams and fake news using text classification. Security and Privacy. 2018; 1(1): e9.
Ahmed H, Traore I, Saad S. Detection of online fake news using n-gram analysis and machine learning techniques. International conference on intelligent, secure, and dependable systems in distributed and cloud environments. 2017. p. 127-38. Springer.