Fake News Detection in Machine Learning Hybrid Model
P. Chandana1, K. Sree Vijaya Lakshmi2

1P.Chandana, CSE, VR Siddhartha Engineering College, Vijayawada, India.
2K.Sree Vijaya Lakshmi, CSE, VR Siddhartha Engineering College, Vijayawada, India. 

Manuscript received on May 02, 2020. | Revised Manuscript received on May 21, 2020. | Manuscript published on May 30, 2020. | PP: 2668-2671 | Volume-9 Issue-1, May 2020. | Retrieval Number: A3067059120/2020©BEIESP | DOI: 10.35940/ijrte.A3067.059120
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: Now a day’s prediction of fake news is somewhat an important aspect. The spreading of fake news mainly misleads the people and some false news that led to the absence of truth and stirs up the public opinion. It might influence some people in the society which leads to a loss in all directions like financial, psychological and also political issues, affecting voting decisions during elections etc. Our research work is to find reliable and accurate model that categorize a given news in dataset as fake or real. The existing techniques involved in are from a deep learning perspective by Recurrent Neural Network (RNN) technique models Vanilla, Gated Recurrent Unit (GRU) and Long Short-Term Memories (LSTMs) by applying on LAIR dataset. So we come up with a different plan to increase the accuracy by hybridizing Decision Tree and Random Forest.
Keywords: Deep Learning, Decision Tree, Random Forest.
Scope of the Article: Machine Learning