AI-BASED PETTITION CLASSIFICATION & TRACKING SYSTEM(NYAYASETU)

Citizen grievance redressal plays a vital role in democratic governance, and the timely triage of petitions is important to reduce delays and improve the allocation of government resources. The proposed AI-powered NyayaSetu system enhances civic petition classification using advanced natural language processing and machine learning techniques. Unlike traditional systems that rely only on manual classification or basic keyword matching, this system uses a SentenceTransformer model to capture the deep semantic context of petition text, improving urgency detection accuracy. To address the challenge of classifying high-dimensional text representations, the system applies a Support Vector Classifier (SVC) optimized via stratified cross-validation on curated datasets, reducing the need for manual triage. In addition, automatic language detection and translation techniques are used to support multilingual inputs and increase system accessibility. The framework also combines the classification model with an automated email notification pipeline to improve routing efficiency to appropriate government departments. Furthermore, the system supports full-stack web deployment for real-time petition submission and tracking in resource-constrained environments. This approach helps government staff take immediate action on critical issues, reduce triage bottlenecks, and improve overall transparency in the grievance redressal pipeline.

Artificial Intelligence, Civic Petition Classification, Natural Language Processing, Sentence Embeddings, Support Vector Classifier, Urgency Triage, E-Governance, Civic Technology.

1.
S. Dumais, J. Platt, D. Heckerman, and M. Sahami, “Inductive learning algorithms and representations for text categorization,” Proceedings of the International Conference on Information and Knowledge Management (CIKM), pp. 148–155, 1998.
2.
F. Sebastiani, “Machine learning in automated text categorization,” ACM Computing Surveys, vol. 34, no. 1, pp. 1–47, 2002.
3.
T. Joachims, “Text categorization with Support Vector Machines: Learning with many relevant features,” Proceedings of the European Conference on Machine Learning (ECML), pp. 137–142, 1998.
4.
J. Devlin et al., “BERT: Pre-training of deep bidirectional transformers for language understanding,” Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics (NAACL-HLT), pp. 4171–4186, 2019.
5.
N. Reimers and I. Gurevych, “Sentence-BERT: Sentence embeddings using Siamese BERT-Networks,” Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP-IJCNLP), pp. 3982–3992, 2019.
6.
Ministry of Electronics and Information Technology (Government of India), “MyGov: Citizen Engagement Platform,” 2014. [Online]. Available: mygov.in
7.
European Commission, “European Citizens’ Initiative: Official Register,” 2012. [Online]. Available: europa.eu/citizens-initiative
8.
K. Song et al., “MPNet: Masked and Permuted Pre-training for Language Understanding,” Advances in Neural Information Processing Systems (NeurIPS), 2020.