Method for Protecting Users From Fake News Using Hybrid Evaluation Methods Combining Artificial Intelligence and User Experience

Aim: In today’s digital society, the growing problem of disinformation, which spreads faster than ever before through social media, poses a serious challenge. The aim of the study was to develop a method for protecting users against fake news by combining artificial intelligence solutions with human knowledge and experience. The authors assumed that effective counteraction against disinformation requires not only advanced technologies but also active involvement of users, who are able to detect subtleties that might escape automated systems. Project and methods: As part of the project, a system was developed to create a database of disinformation articles. An initial verification of the content was carried out by experts, followed by user evaluations, whose responses were used to train machine learning classification models. Feedforward neural networks were applied and trained on data enriched with text complexity indicators such as the Pisarek index, FOG index, and Flesch readability scores. An important element of the system was also the profiling of users based on their knowledge and competencies, which allowed for more accurate matching of the content being evaluated. Results: The results indicated that the neural network achieved a classification accuracy of 84%, which was considered a very good result given the complexity of detecting disinformation. Qualitative analysis revealed that fake news is characterized by its ubiquity, simplicity of message, and emotional appeal, making it exceptionally effective at spreading. The research also showed that even highly knowledgeable users are not completely immune to manipulation, particularly when emotionally charged social events are involved. It was confirmed that fake news most often concerns political, economic, and social topics and that its goals are both to achieve political influence and economic gain. Conclusions: The conclusions drawn from the study indicate that complete protection against disinformation is impossible; however, it is possible to mitigate its effects through appropriate user education and technological development. Media literacy and the development of critical content analysis skills are essential to strengthening society’s resilience to false information. The hybrid approach, combining artificial intelligence with human expertise, proved to be an effective solution, although it requires continuous improvement of models and analytical methods. The article emphasizes the necessity for further research in this area and the importance of a systemic approach combining technology, education, and social responsibility.