Cyber Security for Hoax News Detection with Similarity Algorithm

Hoax news is false information disseminated to deceive or mislead audiences, often with the aim of swaying opinions or creating confusion. The rise of social media has amplified the spread of hoax news, particularly in sensitive areas such as politics and health. In response to this growing issue, this paper proposes a Natural Language Processing (NLP) approach of detecting hoax news using the Smith-Waterman similarity algorithm. By comparing news content with a curated dataset of verified hoaxes, the system calculates a similarity score to assess the likelihood of the news being false. The results of this study show that news articles analyzed using the Smith-Waterman algorithm achieve a high accuracy, with a similarity score exceeding $93 \%$ for news inputs over 100 words. Furthermore, the proposed system demonstrates an efficient processing time, completing the analysis in approximately 6.57 seconds. These findings underscore the algorithm’s potential for real-time application in detecting fake news on social media and other digital platforms. This research aims not only to enhance the technical capabilities of hoax detection systems but also to foster greater media literacy and a more informed public.