Scientists Develop Algorithm to Quickly Rid Social Media of Fake News
Credit: Fotolia
A new system for detecting fake news has been developed by scientists at the North Carolina State University and the Army Research Office.
The model which analyses the spread of competing information on social media and the Internet can be used remove false information and replace it with accurate information in every field, from cyber security to public health.
Wenye Wang, co-author of the paper and a professor of electrical and computer engineering at NC State, said: “Whether in the IoT or on social networks, there are many circumstances where old information is circulating and could cause problems - whether it's old security data or a misleading rumor. Our work here includes a new model and related analysis of how new data can displace old data in these networks.”
According to lead author Jie Wang, the researchers' work can be used to determine the best places to inject new data into a network so that the old data can be eliminated faster.
In their paper published in IEEE/ACM Transactions on Networking, the researchers show that a network's size plays an important role in how quickly 'good' information can displace 'bad' one. But this does not mean that a large network is better or worse than a small one. New data can be disseminated very quickly in a highly interconnected network. The larger the network, the faster this process is.
In networks with a limited number of key nodes, those nodes are bottlenecks. As a result, the larger such a network is, the slower the new data will be disseminated.
The researchers also developed an algorithm that can be used to identify the point in a network that would allow it to spread new data throughout the network most quickly.
“Practically speaking, this could be used to ensure that an IoT network purges old data as quickly as possible and is operating with new, accurate data,” Wenye Wang said.
He added that these findings are also applicable to online social networks, and could be used to facilitate the spread of accurate information regarding subjects that affect the public and combat misinformation online.
mrt/ ekr/ kap/
tr. RL
Przed dodaniem komentarza prosimy o zapoznanie z Regulaminem forum serwisu Nauka w Polsce.
