Hybrid Text Classification Method for Fake News Detection
Prabhjot Kaur1, Rajdavinder Singh Boparai2, Dilbag Singh3
1Prabhjot Kaur, Department of , Computer Science and Applications in Big Data specialization from Chandigarh University, Gharuan, India.
2Rajdavinder Singh Boparai, Assistant Professor in Apex Institute of Technology of Chandigarh University, India.
3DilbagSingh, Department of Computer Science and Engineering, Thapar Institute of Engineering and Technology, Patiala (Punjab), India.
Manuscript received on 18 June 2019 | Revised Manuscript received on 25 June 2019 | Manuscript published on 30 June 2019 | PP: 2388-2392 | Volume-8 Issue-5, June 2019 | Retrieval Number: E7632068519/19©BEIESP
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© 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: Fake news will be news, stories or scams made to purposely misguide or delude perusers. As a rule, these accounts are made to impact individuals’ perspectives, push a political motivation or cause disarray and can regularly be a gainful business for online distributers. Fake news stories can swindle individuals by looking like believed sites or utilizing comparative names and web delivers to trustworthy news associations. The fake news detection has the three phases which are preprocessing, feature extraction and classification. In the previous time Support Vector Machine (SVM) classification is applied for the fake news detection. To improve accuracy of the fake news hybrid classification model is designed in this research work. The proposed model is implemented in Python and results are analyzed in terms of accuracy, precision and recall. Experimental analysis shows that the proposed method outperforms competitive techniques.
Keywords: Fake news, SVM, Hybrid classifier
Scope of the Article: Classification