Automatic classification of legislative documents

Use case ID: 007

Author: IT Department, Chamber of Deputies of Italy

Date: 22 May 2024

Objective: 

Provide an automatic classification, according to the EuroVoc thesaurus, of Italian legislative documents from the Italian Official Gazette.

Actors: 

• Business units
• Classification system

Prerequisites:

• Existing database of legislative documents as training data
• Knowledge of the EuroVoc thesaurus
• AI classification model trained to assign labels to the documents

Scenario:

1. A new legislative document is submitted and inserted inside the database.
2. The classification model suggests the best EuroVoc labels for that act.
3. The user can either accept or modify the list of labels associated with the act.
4. The labels associated with the act are stored as metadata.

Expected results:

• The process of assigning EuroVoc labels to documents is more efficient.

Potential challenges:

• Unbalanced dataset
• Non-interpretable model (e.g. neural networks)
• Long training time (weakly scalable in training data size)
• Some kinds of models could not be robust to outliers
• Avoid overfitting

Data requirements:

• Legislative documents database

Integrations with other systems:

• Legislative documents database

Success metrics:

• Reduction of the time needed to classify legislative documents
• Percentage of legislative documents classified without any modification to the labels made by humans
• Average response time needed to classify