Novel approach for predicting fake news stance detection using large word embedding blending and customized CNN model
Abdulaziz Altamimi, Lipeng Song, Jawad Rasheed, Jawad Rasheed, Jawad Rasheed · 2024
Read Novel approach for predicting fake news stance detection using large word embedding blending and customized CNN model by Abdulaziz Altamimi, Lipeng Song, Jawad Rasheed, Jawad Rasheed, Jawad Rasheed (2024) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-11643300.txt.
Description
A blend of word-meaning vectors powers a fake news stance detector described in this 2024 paper. False stories spread faster than readers can check them, harming reputations and trust. The system combines three popular embedding methods into rich word features, trims them to the most useful ones, and feeds them to a tailored neural network.
On a standard challenge dataset the model reached about 94.6 percent accuracy, with precision and recall both above 95 percent. It beat machine learning, deep learning, and ensemble rivals in the comparison. A second test on an Arabic fake news collection confirmed the approach travels across languages. The authors offer it as an early-warning tool against misinformation.
Catalog record
| CREATOR | Abdulaziz Altamimi, Lipeng Song, Jawad Rasheed, Jawad Rasheed, Jawad Rasheed |
|---|---|
| YEAR | 2024 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 77 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |