Machine Learning Mitigates the Spread of Fake News

The spread of false news must be prevented because it has the potential to have a negative impact. Incorrect information can lead a person to make the wrong decision or act.

The following article was translated using both Microsoft Azure Open AI and Google Translation AI.

A number of youths signed the Bandung Anti Hoax declaration held by the Indonesian Anti-Defamation Society (Mafindo) on a motorized vehicle-free day on Jalan Ir Djuanda, Bandung City, West Java, Sunday (31/3/2019).

JAKARTA, KOMPAS — The development of digital technology has made it easy for false information to circulate. Machine learning or learning machines with block chain technology or blockchain can be used to help mitigate the spread of fake news.

The latest research at Binghamton University, State University of New York, United States, is developing a study by offering tools to recognize false information patterns. This helps content creators detect inaccuracies that occur.

”I hope this research helps us educate more people to know the pattern. That way, they know when to verify something before sharing it and are more alert to discrepancies between the title and the content itself," said assistant professor of management information systems at Binghamton University, Thi Tran, quoted from Sciencedaily.com, Wednesday (2/8/2023) ).

FX LAKSANA AGUNG SAPUTRA

Hoax photo of the president's decision on the establishment of a state financial emergency.

This research proposes a machine learning system—part of artificial intelligence (AI)—which uses data and algorithms to mimic the way humans determine content that can harm readers. One example is the information touting fake alternative treatments during the height of the Covid-19 pandemic.

This learning machine framework uses data and algorithms to identify indicators of misinformation. It then uses these examples to improve the detection process.

Also read: Lost of Lives Due to Rampant Hoaxes

"We tend to be concerned about fake news if it causes losses that affect readers or the audience. If people feel there is nothing wrong, they tend to share false information," he said.

Based on the information gathered, machine learning systems can help mitigate fake news by distinguishing which messages are likely to be the most damaging if allowed to spread, Tran said. The level of education can be a factor for someone to believe the wrong information message or not.

This machine learning framework uses data and algorithms to identify indicators of misinformation. It then uses this example to improve the detection process.

"The factors will be studied by a machine learning system. For example, the system can suggest, based on your message features and background, that there is a 70 percent chance that you will become a victim of that false information message," he explained."

Tran proposed surveying 1,000 people from two groups, namely fake news checkers (government organizations, news agencies and social network administrators) and content users who could be exposed to fake news messages. The survey will describe the existing blockchain system and measure participants' willingness to use the system in different scenarios.

"The research model I built allows us to test different theories and then prove which is the best way to convince people to use something from blockchain to combat misinformation," he says.

Also read: Come on, Beat the Fake News

KOMPAS/WAWAN H PRABOWO

Under the flyover in the Rawa Panjang area, Bekasi City, West Java, is decorated with murals to fight the spread of false information or hoaxes in the community, as seen on 28 February 2021.

The spread of false news must be prevented because it has the potential to cause negative impacts. Misinformation can cause someone to make wrong decisions or actions.

In another study, researchers at West Virginia University, USA, Dana Coester, said that the problem of fake news is not just a media issue. "It is also a social and political issue rooted in technology. Solving this problem requires interdisciplinary collaboration," she said.

The use of a machine learning system is necessary to analyze text and generate scores representing the likelihood of each article containing fake news. These scores are accompanied by descriptions that explain the ranking and provide transparency in the assessment.