Enhancing E-Government through Sentiment Analysis: A Dual Approach Using Text and Facial Expression Recognition

In the era of digital governance, understanding public sentiment towards governmental initiatives is crucial for policy success and citizen engagement. This paper presents a novel approach to gauge public opinion by employing Convolutional Neural Networks (CNN) and sentiment analysis techniques to analyze both textual feedback and facial expressions related to government schemes. The dual-modality system aims to offer a comprehensive sentiment analysis framework that recognizes the positive or negative valence of textual responses and facial cues from images uploaded by the public. By integrating this sentiment feedback into e- government platforms, policymakers can gain real-time insights into the efficacy of their initiatives and foster a more responsive and participatory governance environment. This research aims to bridge the gap between government action and citizen perception, providing an interactive platform for governments to stay attuned to the public's reactions to their policies. The results of this study have the potential to revolutionize the feedback mechanisms within e-governance systems, enabling a more dynamic and democratic interaction between the state and its citizens