Answers are grounded in this paper and cite their sources.
The internet explosion and penetration have amplified the Fake news problem that existed even before internet penetration. This becomes more of a concern, if it is health-related news. To address this issue, the research aims to propose Content based (CBM) and Feature Based Models (FBM). The difference between both the models is in the input provided. The CBM only takes the news content as the input whereas the FBM along with the contents also takes two readability features as the input. Under each category the performance of five traditional machine learning techniques: Decision Tree, Random Forest, Support Vector Machine, Adaboost-Decision Tree and Adaboost-Random Forest is compared with two hybrid Deep Learning approaches namely CNN-LSTM and CNN-BiLSTM. Fake News Healthcare data set comprising of 9581 articles is utilized for the study. As it is a highly imbalanced dataset, Easy Data Augmentation technique is used to balance this dataset. Experimental results demonstrate that Feature Based Models performed better than Content Based Models. Amongst the proposed FBM, Hybrid CNN - LSTM model had F1 score of 97.09% and Adaboost-Random Forest had F1 Score of 98.9%. Thus Adaboost-Random Forest under FBM is the best performing model for classification of fake news.
No takes yet. Share an insight, caveat, or question.
Mahara et al. (2023) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: