Hoax News Classification using Machine Learning Algorithms
Sy.Yuliani1, Shahrin Sahib2, Mohd Faizal Bin Abdollah3, Fariska Z. Ruskanda4
1SY.Yuliani, Information Security and Networking Research Group, Faculty of Information Communication Technology, University Teknikal Malaysia Melaka, Malaysia.
2Shahrin Sahib, Information Security and Networking Research Group, Faculty of Information Communication Technology, University Teknikal Malaysia Melaka, Malaysia.
3Mohd Faizal Bin Abdollah, Information Security and Networking Research Group, Faculty of Information Communication Technology, University Teknikal Malaysia Melaka, Malaysia.
4Fariska Z. Ruskanda, School of Electrical Engineering and Informatics, School of Electrical Engineering and Informatics, Indonesia.
Manuscript received on November 18, 2019. | Revised Manuscript received on December 15, 2019. | Manuscript published on December 30, 2019. | PP: 3938-3944 | Volume-9 Issue-2, December, 2019. | Retrieval Number: B3753129219/2019©BEIESP | DOI: 10.35940/ijeat.B3753.129219
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Hoax news on social media has had a dramatic effect on our society in recent years. The impact of hoax news felt by many people, anxiety, financial loss, and loss of the right name. Therefore we need a detection system that can help reduce hoax news on social media. Hoax news classification is one of the stages in the construction of a hoax news detection system, and this unsupervised learning algorithm becomes a method for creating hoax news datasets, machine learning tools for data processing, and text processing for detecting data. The next will produce a classification of a hoax or not a Hoax based on the text inputted. Hoax news classification in this study uses five algorithms, namely Support Vector Machine, Naïve Bayes, Decision Tree, Logistic Regression, Stochastic Gradient Descent, and Neural Network (MLP). These five algorithms to produce the best algorithm that can use to detect hoax news, with the highest parameters, accuracy, F-measure, Precision, and recall. From the results of testing conducted on five classification algorithms produced shows that the NN-MPL algorithm has an average of 93% for the value of accuracy, F-Measure, and Precision, the highest compared to five other algorithms, but for the highest Recall value generated from the algorithm SVM which is 94%. the results of this experiment show that different effects for different classifiers, and that means that the more hoax data used as training data, the more accurate the system calculates accuracy in more detail.
Keywords: Hoax News, Text classification, Machine Learning, Support Vector Machine, Naïve Bayes. Decision Tree, Logistic Regression, Stochastic Gradient Descent, Neural Network –MLP.