AI Appeals Processor: A Deep Learning Approach to Automated Classification of Citizen Appeals in Government Services

TL;DR

This paper introduces AI Appeals Processor, a deep learning system that automates citizen appeal classification, significantly improving processing speed and accuracy over manual methods.

Contribution

It presents a novel microservice-based system integrating NLP and deep learning for automated appeal classification and routing.

Findings

Word2Vec+LSTM achieves 78% accuracy

Reduces processing time by 54%

Outperforms transformer-based models in efficiency

Abstract

Government agencies worldwide face growing volumes of citizen appeals, with electronic submissions increasing significantly over recent years. Traditional manual processing averages 20 minutes per appeal with only 67% classification accuracy, creating significant bottlenecks in public service delivery. This paper presents AI Appeals Processor, a microservice-based system that integrates natural language processing and deep learning techniques for automated classification and routing of citizen appeals. We evaluate multiple approaches -- including Bag-of-Words with SVM, TF-IDF with SVM, fastText, Word2Vec with LSTM, and BERT -- on a representative dataset of 10,000 real citizen appeals across three primary categories (complaints, applications, and proposals) and seven thematic domains. Our experiments demonstrate that a Word2Vec+LSTM architecture achieves 78% classification accuracy while reducing processing time by 54%, offering an optimal balance between accuracy and computational efficiency compared to transformer-based models.