Spot that fake!
Problem being addressed
News in social media such as Twitter has been generated in high volume and speed. However, very few of them are labeled (as fake or true news) by professionals in near real time.
A novel two-path deep semi-supervised learning framework where both labeled data and unlabeled data are used jointly to train the model, enhance the detection performance and accomplish timely fake news detection in the case of limited labeled data.
Advantages of this solution
Experimental results demonstrate the effectiveness of the proposed framework even with very limited labeled data.
Solution originally applied in these industries
Possible New Application of the Work
The proposed framework can show good results on other NLP tasks such as sentiment analysis, which will allow better track of customer satisfaction and quick adjustment of the marketing strategies.
Source URL: #############