LegisAI: AI-Powered Legislative Comment Analysis

Main Article Content

Dr. Ruchi Vyas

Abstract

The increasing volume of stakeholder feedback in legislative processes makes manual analysis inefficient and error-prone. This paper presents LegisAl, an Al-based system designed to automatically analyze legislative comments using Natural Language Processing techniques. The system performs sentiment analysis to classify opinions, generates concise summaries of lengthy comments, and visualizes frequently used keywords through word clouds. Transformer-based models such as DistilBERT and DistilBART are utilized to achieve efficient and accurate processing. The proposed solution significantly reduces manual effort and enhances decision-making by providing structured insights. Experimental results demonstrate an approximate accuracy of 85% in sentiment classification with effective summarization performance.

Article Details

Section

Articles

Author Biography

Dr. Ruchi Vyas

Geetanjali Institute of Technical Studies                       

Udaipur, Rajasthan, India

References

[1] Gupta, C. P., & Kumar, V. V. R(2025). Sentiment Analysis : Using different models for monitoring and analyzing customer reviews. Indian Journal of Marketing, 55(5),8. https://doi.org/10.17010/ijom/2025/v55/i5/175017

[2] Kumar, M., Khan, L., & Chang, H. (2025). Evolving techniques in sentiment analysis: a comprehensive review. PeerJ Computer Science, 11, e2592. https://doi.org/10.7717/peerj-cs.2592

[3] Suryawanshi, N. S. (2024). Sentiment analysis with machine learning and deep learning: A survey of techniques and applications. International Journal of Science and Research Archive, 12(2), 005–015. https://doi.org/10.30574/ijsra.2024.12.2.1205

[4] Jena, A. (2025a, August 18). Introduction to Sentiment Analysis in natural language processing (NLP). Knowledge Tank. https://www.projectguru.in/introduction-to-sentiment-analysis-in-natural-language-processing-nlp/

[5] Benni, S. D. (2024). Green Fuel Synthesis from Jatropha curcas Seed Oil: A Computational Approach using Python Programming Language. Journal of Electrical Systems, 20(11s), 3388–3396. https://doi.org/10.52783/jes.8092

[6] Krishna, K. M. R., Somasundaram, K., Arulmozhivarman, P., Immanuel, S. A., & Rajkumar, E. R. (2025). Deep learning for text summarization using NLP for automated news digest. Scientific Reports, 15(1), 36343. https://doi.org/10.1038/s41598-025-20224-1

[7] An evaluation of large language models on text summarization tasks using prompt engineering techniques. (n.d.). https://arxiv.org/html/2507.05123v1

[8] Raj, R. K. M., Vochozka, M., & Sujatha, S. (2025). Sentiment analysis of news: unveiling AI’s role in sustainability and no poverty (SDG1). Discover Sustainability, 6(1). https://doi.org/10.1007/s43621-025-01456-7

[9] Sentiment Analysis: a comprehensive study of computational techniques, applications, and datasets. (2024, December 16). IEEE Conference Publication | IEEE Xplore. https://ieeexplore.ieee.org/document/10860172

[10] Wizrai. (2026, January 30). AI Text Analysis: 6 Best Tools, Techniques & Use Cases [2025]. Wizr AI | Build Autonomous Enterprises Powered by AI. https://wizr.ai/blog/ai-text-analysis-tools-techniques-use-cases/