The escalating dissemination of fake news across social media networks has emerged as a concerning societal issue and a threat to cyber physical systems. Bots, often employed to propagate such misinformation, present a formidable challenge in their detection and elimination. Bot prediction have been pivotal in identifying and curbing these deceptive bot activities within social media networks. Twitch’s live streaming content is readily scrapable and totally accessible. But quite understudied. Recent studies scrutinized these frameworks, revealing significant strides in their development while acknowledging the need for further enhancements in both predictions for proactive measures. FusionBotSentinel proposes a novel architecture that underscores the imperative for future research to concentrate on fortifying these frameworks, ensuring they are more resilient and adaptable in mitigating and predicting the spread of fake news by social bots. Another focus is on enhancing the effectiveness of deep learning models through a refined understanding of data quality with a largest dataset available and employing better hybrid techniques that bolster the generalizability and robustness helping in forecasting bot activities in combatting this escalating problem within cyber physical systems. Since bots are seen to be the source of the present problems with cyber physical systems, including privacy, security, safety, and ethical difficulties, it is necessary to recognize these gaps. Our suggested FusionBotSentinelprovides a revolutionary significance by contributing to in combatting fake news in the society by achieving up to 99% in accuracy, 98% in precision, 100% in recall, 99% in sensitivity with F1 score as 99% in social bot prediction offering 20% more efficiency when compared to the most advanced existing models proving its superiority.