Taiwanese Researchers Develop Model to Detect Internet Addiction

A research team from Taiwan has created a groundbreaking machine-learning model that utilizes electroencephalography (EEG) to identify Internet addiction with an impressive accuracy rate of 86 percent. The announcement was made during a news conference, where lead researcher Huang Hsu-wen detailed the study’s findings.

The study, which analyzed the resting-state EEG patterns of 92 participants—42 diagnosed with Internet addiction and 50 healthy controls—revealed significant differences in brain activity. Huang explained that the addicted group exhibited elevated levels of phase synchronization in their EEG readings, a finding that suggests that Internet addiction disrupts critical neural systems involved in inhibitory and reward pathways.

According to Huang, the significance of these findings lies in their potential for early detection. The changes in EEG patterns occur before the behavioral symptoms of addiction become apparent. This means that integrating EEG testing with machine-learning classification models could allow for the identification of early risk signals. As a result, schools and medical institutions could potentially implement targeted interventions more effectively.

Internet addiction is characterized by excessive online engagement, an inability to limit online activity, and feelings of discomfort when disconnected from the Internet. This definition is supported by the research published in May 2023 in the journal Psychological Medicine.

The study involved collaboration among various institutions. Wu Shun-chi, a professor at National Tsing Hua University, and Huang Chih-mao, an associate professor at the University of Hong Kong, contributed to the research, along with other research institutions in Taiwan and abroad.

Huang emphasized the importance of these findings in a world where online engagement continues to grow. The application of this technology could pave the way for more precise interventions aimed at mitigating the adverse effects of Internet addiction, ultimately enhancing mental health and well-being for those at risk.

As the digital landscape evolves, understanding and addressing Internet addiction through innovative approaches like machine learning and EEG analysis will be crucial in fostering healthier online habits and promoting overall psychological health.