| Issue |
MATEC Web Conf.
Volume 395, 2024
2023 2nd International Conference on Physics, Computing and Mathematical (ICPCM2023)
|
|
|---|---|---|
| Article Number | 01008 | |
| Number of page(s) | 7 | |
| DOI | https://doi.org/10.1051/matecconf/202439501008 | |
| Published online | 15 May 2024 | |
DDCO model based false news detection research
1 Xi'an Key Laboratory of Human-Machine Integration and Control Technology for Intelligent Rehabilitation, Xijing University, Xi'an, China
2 Engineering University of PAP, Xi'an, China
* Corresponding author: weibin82@126.com
With the rapid development of the information age, while the popularity of social media brings great convenience, it also brings some negative effects, such as the spread of false news. At present, the identification of fake news is still based on the personal screening ability, therefore, the intelligent and information-based automatic detection algorithm has become one of the hot issues of current research. Based on the characteristics of DCAN and DEFEND models, this paper proposes an novel model DDCO, which uses multi-layer collaborative attention mechanism to extract the most relevant information from the three dimensions of sentence level, word level and sentence-comment level respectively. Finally, the model designed in this paper is tested on Weibo and Twitter data sets, and the results show that the DDCO has a higher accuracy than the existing models, which provides an important reference for false news detection.
Key words: Cooperative attention mechanism / DDCO / False news detection
© The Authors, published by EDP Sciences, 2024
This is an Open Access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.