Published September 9, 2026 | Version 1.1.0
Other Restricted

A Natural Language Processing Framework for Bias Indicator Analysis in Legal Text: A Law-Sensitive Severity Ladder and Benchmark Evaluation Across Eight English Legal Datasets

  • 1. COMSATS University Islamabad Pakistan, Lahore Campus

Description

This repository contains the research code, computational implementation, derived research materials, experimental configurations, and supplementary materials associated with the study “A Natural Language Processing Framework for Bias Indicator Analysis in Legal Text: A Law-Sensitive Severity Ladder and Benchmark Evaluation Across Eight English Legal Datasets.”

This version provides the revised reproducibility package prepared in response to the technical requirements of PeerJ Computer Science. It includes the computational code and derived research materials used to support preprocessing, bias-indicator analysis, severity scoring, statistical evaluation, and benchmark experiments reported in the manuscript.

The study investigates textual bias-indicator signals across eight publicly available English legal datasets: BillSum, CaseHOLD, CaseSumm, ECtHR, EUR-LEX, LEDGAR, SCOTUS, and UnfairTOS. The authors did not collect the original legal documents. After dataset-specific filtering and preprocessing, the resulting working corpus contained 276,240 records.

The original third-party datasets are not claimed as original work by the authors and remain subject to their respective licenses, terms of use, and attribution requirements. Users should obtain third-party datasets from their respective original or authorized sources.

The supplementary package is provided to facilitate reproducibility, methodological verification, and future research in legal natural language processing and computational legal text analysis. The accompanying README provides information about datasets and their sources, code, software requirements, implementation procedure, methodology, usage instructions, citations, and licensing considerations.

Files

Restricted

The record is publicly accessible, but files are restricted. Log in to check if you have access.

Additional details

Software

Programming language
Python
Development Status
Active