Systematic Approach for Detection of Fake News on Social Media Platform

The emergence of social media has transformed how information is shared, but it has also made it easier to spread false content. Allowing untrue information to circulate without scrutiny can lead to serious consequences, causing confusion, eroding trust in reliable sources, and weakening the foundations of truth and logic. It’s crucial to urgently address the detection and prevention of misleading content on social media. The rise of social media spammers is a significant problem, as they take advantage of these platforms to disseminate false information. Their unethical practices not only trick innocent users but also pose substantial risks to society, public discourse, and even democratic processes. Additionally, the active nature of social media, dealing with real-time data, raises concerns about the rapid distribution of rumours. Early control over the spread of false information is imperative. To tackle these issues, it's essential to promptly address and prevent the dissemination of misleading information on various social media platforms. Our objective is to thoroughly investigate the current state of Twitter false information detection. We have outlined an introduction, relevant literature review, problem statement, research objectives, and proposed methodology. We aim to develop an innovative false information detection model called Deep Twin Attention N-gram-assisted CNN-BiLSTM with Boosted Hunger Games Search optimization (DTwiN_CBiB) to extract valuable features and classify fake news.