MANOBHAV: SENTIMENT ANALYSIS OF COMMENTS RECEIVED THROUGH E-CONSULTATION MODULE

The growing adoption of digital governance platforms necessitates effective mechanisms for analysing large-scale citizen feedback. The e-Consultation module of the MCA21 portal enables stakeholders to provide comments and suggestions on draft legislations and proposed amendments. However, the sheer volume of responses poses challenges in ensuring that each comment is systematically reviewed without bias or oversight. To address this, we propose an AI-assisted framework that leverages natural language processing (NLP) techniques for sentiment analysis, automatic summarization, and keyword visualization through word clouds. The system aims to classify stakeholder inputs into sentiment categories (positive, negative, neutral), generate concise summaries that capture the essence of each comment, and visualize frequently occurring terms to identify recurring themes. This approach not only enhances efficiency in legislative review but also ensures inclusivity, transparency, and evidence-based decision-making. By reducing manual effort and highlighting critical patterns in stakeholder feedback, the proposed solution contributes to more robust and citizen-centric policy formulation.