The era of digital information has witnessed the alarming surge of disinformation, posing a serious challenge to the reliability of information and societal cohesion. In response, the need for robust and efficient methods to identify false information has become paramount. This paper introduces an innovative Hybrid Deep Learning approach that harnesses the capabilities of deep neural networks to improve the precision and dependability of information analysis within information systems. This approach combines Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs), with a particular emphasis on the examination of textual and multimedia content. By integrating both CNNs and RNNs, this method adeptly captures spatial and temporal features, enabling the evaluation of textual and visual content from diverse sources. Moreover, the approach incorporates attention mechanisms to assess the relevance of different elements within the content, facilitating the fine-grained differentiation between authentic and deceptive information. A comparative examination of several methodologies has been carried out. The results exhibit a substantial enhancement in the precision of disinformation identification when compared to conventional machine learning methods and standalone deep learning models.