Hybrid Deep Learning for Legal Text Analysis: Predicting Punishment Durations in Indonesian Court Rulings

TL;DR

This paper presents a hybrid deep learning model combining CNN and BiLSTM with attention to predict court sentence durations from Indonesian legal texts, improving transparency and understanding in the legal system.

Contribution

It introduces a novel hybrid NLP model tailored for legal text analysis and demonstrates its effectiveness in predicting punishment durations in Indonesian court rulings.

Findings

Achieved an R-squared score of 0.5893 in prediction accuracy.

Focusing on top 30% frequent tokens enhances model performance.

Improved text normalization significantly boosts prediction results.

Abstract

Limited public understanding of legal processes and inconsistent verdicts in the Indonesian court system led to widespread dissatisfaction and increased stress on judges. This study addresses these issues by developing a deep learning-based predictive system for court sentence lengths. Our hybrid model, combining CNN and BiLSTM with attention mechanism, achieved an R-squared score of 0.5893, effectively capturing both local patterns and long-term dependencies in legal texts. While document summarization proved ineffective, using only the top 30% most frequent tokens increased prediction performance, suggesting that focusing on core legal terminology balances information retention and computational efficiency. We also implemented a modified text normalization process, addressing common errors like misspellings and incorrectly merged words, which significantly improved the model's performance. These findings have important implications for automating legal document processing, aiding both professionals and the public in understanding court judgments. By leveraging advanced NLP techniques, this research contributes to enhancing transparency and accessibility in the Indonesian legal system, paving the way for more consistent and comprehensible legal decisions.