Machine Learning, Blockchain Could Combat the Spread of Fake News, New Study Says

Binghamton University's School of Management (SOM) has conducted research that proposes solutions to combat the spread of fake news using a combination of machine learning and blockchain technology.

Led by Thi Tran, assistant professor of management information systems, the study emphasizes the importance of addressing the potential harm caused by misinformation.

Identifying the Scale of Harm

The research aims to develop a systematic approach to identify the scale of harm that specific content could inflict on its audience, focusing on the most damaging offenders.

For instance, during the COVID-19 pandemic, false information about alternative treatments circulated, diverting attention from the importance of vaccines.

"We're most likely to care about fake news if it causes a harm that impacts readers or audiences. If people perceive there's no harm, they're more likely to share the misinformation," said Thi Tran.

"The harms come from whether audiences act according to claims from the misinformation, or if they refuse the proper action because of it. If we have a systematic way of identifying where misinformation will do the most harm, that will help us know where to focus on mitigation," he added.

The proposed machine learning framework, a division of artificial intelligence (AI), aims to utilize data and algorithms to identify signs of misinformation and enhance the detection process.

The system can accurately predict an individual's susceptibility to specific misinformation messages by considering user characteristics, including education level and political beliefs. This harm index will assess the potential severity of damage a person could experience if exposed to and influenced by fake news.

Vulnerability to Misinformation

Tran underlines the significance of user characteristics in determining their vulnerability to misinformation. The machine learning system can personalize recommendations based on message attributes, the individual's personality, and background, providing insights into the likelihood of falling victim to particular misinformation.

While blockchain technology has previously been examined as a tool to combat fake news, Tran's research delves deeper by investigating user receptiveness to such systems. The research model aims to discover the most compelling approach to persuade people to adopt blockchain technology in the fight against misinformation.

Tran's approach involves surveys among two groups: fake news mitigators, consisting of government organizations, news outlets, and social network administrators; and content users who could potentially encounter fake news messages.

Participants' readiness to adopt existing blockchain systems in different situations will be evaluated through these surveys. The traceability aspect of blockchain technology proves exceptionally beneficial in pinpointing and categorizing sources of misinformation, leading to enhanced pattern recognition and detection capabilities.

Tran's research aims to raise awareness among individuals about recognizing patterns of misinformation and being cautious about sharing unverified content. Tran's work was published in two Disruptive Technologies in Information Sciences VI papers.