Deep Learning Based Fake News AI Detection：Evidence From Taiwan and USA News Report

• Main Authors: HU, LIN-LUNG, 胡林辳
• Other Authors: WANG, CHIH-CHIEN
• Format: Others
• Language: zh-TW
• Published: 2019
• Online Access: http://ndltd.ncl.edu.tw/handle/88rg7x

碩士 === 國立臺北大學 === 資訊管理研究所 === 107 === In recent years, because the Internet acts as a medium, fake news can be quickly spread. Many countries have been seriously affected by fake news. Let fake news detection become an important issue. This study collects two Taiwan refute rumors sites and one American fake news dataset. And use the three methods of deep learning for fake news detection. Gated Recurrent Unit (GRU), Long Short Term Memory (LSTM), and Bidirectional Long Short Term Memory (BLSTM). The experimental results show that deep learning can be used in Taiwan's fake news detection, and the BLSTM method works best. Research experiments reduce the proportion of fake news, simulating 25% and 5% fake news ratios. Let the research sample be closer to the real situation. Finally, this study used a cross-data set test to understand the gap between practice and theory. In the fake news detection research, deep learning can be used in the Traditional Chinese data set. And deep learning is better than machine learning. Bidirectional Long Short Term Memory (BLSTM) is the best method of deep learning in fake news detection. If the model can be applied, more real news and fake news must be collected and collect more news sources.