Fake News Detection by Using Recurrent Neural Network
Megtekintés/
Metaadat
Teljes megjelenítés
Link a dokumentumra való hivatkozáshoz:
Gyűjtemény
Absztrakt
Along with the development of the Internet, social networks and different
communication channels, people can get information quickly and easily. However, in
addition to true and useful news, we must also receive false and untrue information. The
problem of fake news has become a difficult and unresolved problem. In this paper, we
present research results on building a tool to support the fake news detection by using RNN.
Our idea is to apply text classification techniques to fake news detection. We have built a
database of 4 groups of 2 topics about politics (fake news and real news) and about Covid-
19 (fake news and real news). Then use deep learning techniques of RNN to create the
corresponding models. When there is a new news that needs to be verified, we just need to
apply the classification to see which of the four groups they label into to make a decision
whether it is fake news or not. In the future, besides using classification techniques (based
on content analysis), we can combine many other methods such as checking the source,
verifying the author's information, check the distribution process,... to improve the quality of
fake news detection. Along with the development of the Internet, social networks and different
communication channels, people can get information quickly and easily. However, in
addition to true and useful news, we must also receive false and untrue information. The
problem of fake news has become a difficult and unresolved problem. In this paper, we
present research results on building a tool to support the fake news detection by using RNN.
Our idea is to apply text classification techniques to fake news detection. We have built a
database of 4 groups of 2 topics about politics (fake news and real news) and about Covid-
19 (fake news and real news). Then use deep learning techniques of RNN to create the
corresponding models. When there is a new news that needs to be verified, we just need to
apply the classification to see which of the four groups they label into to make a decision
whether it is fake news or not. In the future, besides using classification techniques (based
on content analysis), we can combine many other methods such as checking the source,
verifying the author's information, check the distribution process,... to improve the quality of
fake news detection.